update

.gitignore

@@ -10,6 +10,7 @@ wheels/
 .venv
 
 # data
+.checkpoints
 .data
 data
 runs

.vscode/launch.json

@@ -0,0 +1,16 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+
+        {
+            "name": "Python Debugger: Current File",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "src/train.py",
+            "console": "integratedTerminal"
+        }
+    ]
+}

pyproject.toml

@@ -1,5 +1,5 @@
 [project]
-name = "study-asr"
+name = "audio-model"
 version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
@@ -8,17 +8,22 @@ dependencies = [
     "ipython>=9.10.1",
     "librosa>=0.11.0",
     "matplotlib>=3.10.8",
+    "mutagen>=1.47.0",
     "numpy>=2.4.4",
     "pandas>=3.0.2",
     "pillow>=12.2.0",
+    "pydub>=0.25.1",
     "pyrubberband>=0.4.0",
     "setuptools<82",
+    "silero-vad>=6.2.1",
     "tensorboard>=2.20.0",
     "tensorboardx>=2.6.5",
     "torch==2.8.0",
+    "torch-audiomentations>=0.12.0",
     "torchaudio==2.8.0",
     "torchcodec==0.7.0",
     "tqdm>=4.67.3",
+    "webrtcvad>=2.0.10",
 ]
 
 [[index]]

src/dataset.py

@@ -1,22 +1,21 @@
 import random
-import unicodedata
 
 import torch
 from torch import Tensor
 from torch.utils.data import Dataset, DataLoader
 import torchaudio
-from torchaudio.transforms import FrequencyMasking, MelSpectrogram, AmplitudeToDB, Resample, TimeMasking, TimeStretch
+from torch_audiomentations import ApplyImpulseResponse, Gain, PitchShift, LowPassFilter, HighPassFilter, PolarityInversion
+from torchaudio.transforms import Resample, TimeStretch
 from pathlib import Path
-import torchaudio.functional as F
 import pandas as pd
-from typing import Dict, List, TypedDict
-from handle.text_normalizer import collapse_spaces, normalize_extended_uyghur_characters
+from typing import List, TypedDict
+from handle.text_normalizer import clean_input_text
 from tokenizer import ASRTokenizer
 
 
 # 单个样本的数据结构（Dataset.__getitem__ 返回）
 class BatchItem(TypedDict):
-    mel_spec: Tensor          # [n_mels, time] Mel频谱
+    waveform: Tensor          # [time]
     target_ids: Tensor        # [seq_len] 目标文本的token IDs
     target_text: str          # 原始文本
     audio_path: str           # 音频文件路径
@@ -24,9 +23,9 @@ class BatchItem(TypedDict):
 
 # 批量数据的数据结构（collate_fn 返回，DataLoader 输出）
 class Batch(TypedDict):
-    mel_specs: Tensor         # [batch, n_mels, time] padding后的Mel频谱
+    waveforms: Tensor         # [batch, time]
     targets: Tensor           # [batch, max_len] padding后的目标IDs
-    mel_lengths: Tensor       # [batch] 每个样本的实际Mel长度
+    waveform_lengths: Tensor       # [batch] 每个样本的实际Waveform长度
     target_lengths: Tensor    # [batch] 每个样本的实际目标长度
     target_texts: List[str]   # [batch] 原始文本列表
     audio_paths: List[str]    # [batch] 音频路径列表
@@ -41,20 +40,69 @@ class TsvFormat(TypedDict):
     gender: str
     locale: str
 
+class NoiseAugmentor:
+    def __init__(self, noise_root: Path, sample_rate: int=16000):
+        self.sample_rate = sample_rate
+        self.noise_files = list(Path(noise_root).rglob("*.wav"))
+
+    def apply_real_noise(self, waveform: Tensor):
+        # 1. 随机选一个噪音文件
+        noise_path = random.choice(self.noise_files)
+        noise_waveform, sr = torchaudio.load_with_torchcodec(noise_path)
+        
+        # Resample to target sample rate.
+        if sr != self.sample_rate:
+            noise_waveform = Resample(sr, self.sample_rate)(noise_waveform)
+        
+        # Convert to mono if it is setro.
+        if noise_waveform.shape[0] > 1:
+            noise_waveform = noise_waveform.mean(dim=0, keepdim=True)
+        
+        # 3. 截取或填充，使其长度与语音一致
+        sig_len = waveform.shape[1]
+        noise_len = noise_waveform.shape[1]
+        
+        if noise_len >= sig_len:
+            # 随机截取一段
+            start = random.randint(0, noise_len - sig_len)
+            noise_waveform = noise_waveform[:, start:start + sig_len]
+        else:
+            full_noise = torch.zeros_like(waveform)
+            start = random.randint(0, sig_len - noise_len)
+            full_noise[:, start:start + noise_len] = noise_waveform
+            noise_waveform = full_noise
+            
+        # 4. 设定随机信噪比 SNR (5dB 到 20dB)
+        snr_db = random.uniform(5, 20)
+        
+        # 5. 混合
+        return self._mix_at_snr(waveform, noise_waveform, snr_db)
+
+    def _mix_at_snr(self, signal: Tensor, noise: Tensor, snr_db: float):
+        s_p = signal.pow(2).mean()
+        n_p = noise.pow(2).mean()
+        snr_linear = 10**(snr_db / 10)
+        scale = torch.sqrt(s_p / (n_p * snr_linear + 1e-8))
+        
+        noisy = signal + scale * noise
+        # 归一化，防止溢出
+        return noisy / (noisy.abs().max() + 1e-8)
+
 class CommonVoiceDataset(Dataset[BatchItem]):
     def __init__(
         self,
         tsv_path: Path,
         audio_dir: Path,
+        noise_dir: Path,
+        corridor_noise_dir: Path,
         tokenizer: ASRTokenizer,
         sample_rate: int = 16000,
-        n_mels: int = 80 * 4,
         max_audio_len: int = 480000,  # 30秒 @ 16kHz
         augment: bool = True,
-        augment_prob: float = 0.5,  # 数据增强的概率
+        augment_prob: float = 0.5,
     ) -> None:
         super().__init__()
-    
+        self.noise_augmentor = NoiseAugmentor(noise_root=noise_dir, sample_rate=sample_rate)
         self.audio_dir = Path(audio_dir)
         self.tokenizer = tokenizer
         self.sample_rate = sample_rate
@@ -72,22 +120,14 @@ class CommonVoiceDataset(Dataset[BatchItem]):
 
         self.data = self.data.loc[valid_indices].reset_index(drop=True)
 
-        # Mel频谱转换
-        self.mel_transform = MelSpectrogram(
-            sample_rate=sample_rate,
-            n_fft=400,
-            win_length=400,
-            hop_length=160,
-            n_mels=n_mels,
-            f_min=0,
-            f_max=8000,
-            power=3.0
-        )
-        self.amplitude_to_db = AmplitudeToDB()
-
-        # SpecAugment 转换
-        self.time_masking = TimeMasking(time_mask_param=30)  # 遮蔽最多30帧
-        self.freq_masking = FrequencyMasking(freq_mask_param=15)  # 遮蔽最多15个频率
+        self.gain_up = Gain(min_gain_in_db=4, max_gain_in_db=8, p=1.0, output_type='tensor')
+        self.gain_down = Gain(min_gain_in_db=-15, max_gain_in_db=-8, p=1.0, output_type='tensor')
+        self.pitch_up = PitchShift(min_transpose_semitones=1, max_transpose_semitones=4, p=1.0, sample_rate=self.sample_rate, output_type='tensor')
+        self.pitch_down = PitchShift(min_transpose_semitones=-4, max_transpose_semitones=-1, p=1.0, sample_rate=self.sample_rate, output_type='tensor')
+        self.lowpass = LowPassFilter(min_cutoff_freq=1000, max_cutoff_freq=3000, p=1.0, sample_rate=self.sample_rate, output_type='tensor')
+        self.highpass = HighPassFilter(min_cutoff_freq=1000, max_cutoff_freq=3000, p=1.0, sample_rate=self.sample_rate, output_type='tensor')
+        self.apply_ir = ApplyImpulseResponse(ir_paths=corridor_noise_dir, convolve_mode='same', p=1, output_type="tensor")
+        self.polarity_inversion = PolarityInversion(p=1.0, output_type="tensor")
 
     def __len__(self):
         return len(self.data)
@@ -95,42 +135,75 @@ class CommonVoiceDataset(Dataset[BatchItem]):
     def _load_audio(self, audio_path: Path) -> Tensor:
         waveform, sample_rate = torchaudio.load_with_torchcodec(audio_path)
 
+        # Resample to target sample rate.
         if sample_rate != self.sample_rate:
             waveform = Resample(sample_rate, self.sample_rate)(waveform)
 
+        # Convert to mono if it is setro.
         if waveform.shape[0] > 1:
             waveform = waveform.mean(dim=0, keepdim=True)
         
-        max_val = waveform.abs().max()
-        if max_val > 0:
-            waveform = waveform / max_val
+        # Normalization
+        waveform = waveform / max(waveform.abs().max(), 1e-8)
         
+        # Clip waveform exceeds from max length.
         if waveform.shape[1] > self.max_audio_len:
             waveform = waveform[:, :self.max_audio_len]
-
         return waveform
     
-    def _extract_features(self, waveform: Tensor) -> Tensor:
-        """ 提取 Mel 频谱特征 """
-        mel_spec: Tensor = self.mel_transform(waveform)
-        log_mel_spec: Tensor = self.amplitude_to_db(mel_spec)
-        return log_mel_spec.squeeze(0) # [n_mels, time]
-    
     def _augment_waveform(self, waveform: Tensor) -> Tensor:
         if not self.augment or random.random() > self.augment_prob:
             return waveform
         
         # 1. voice Stretch/Compress 
-        if random.random() < 0.5:
-            waveform = self._voice_stretch_or_compress(waveform=waveform)
+        if random.random() < 0.6:
+            waveform = self._stretch_or_compress(waveform=waveform)
         
-        if random.random() < 0.4:
-            waveform = self._add_noise(waveform)
+        if random.random() < 0.5:
+            waveform = self.noise_augmentor.apply_real_noise(waveform)
+        
+        if random.random() < 0.3:
+            waveform = self._time_mask_waveform(waveform=waveform)
+
+        # torch_audiomentations: [1, time] -> [1, 1, time]
+        if waveform.dim() == 2:
+            waveform_3d: Tensor = waveform.unsqueeze(0)
+        # 随机选择一种物理特性增强 (互斥区)
+        choice = random.random()
+        if choice < 0.25: # [0.00 - 0.25] 25% 概率：增益
+            if random.random() < 0.5:
+                waveform_3d = self.gain_up(waveform_3d, sample_rate=self.sample_rate)
+            else:
+                waveform_3d = self.gain_down(waveform_3d, sample_rate=self.sample_rate)
+        elif choice < 0.50: # [0.25 - 0.50] 25% 概率：音高
+            if random.random() < 0.5:
+                waveform_3d = self.pitch_up(waveform_3d, sample_rate=self.sample_rate)
+            else:
+                waveform_3d = self.pitch_down(waveform_3d, sample_rate=self.sample_rate)
+        elif choice < 0.70: # [0.50 - 0.70] 20% 概率：低通
+            waveform_3d = self.lowpass(waveform_3d, sample_rate=self.sample_rate)
+        elif choice < 0.85: # [0.70 - 0.85] 15% 概率：高通
+            waveform_3d = self.highpass(waveform_3d, sample_rate=self.sample_rate)
+        elif choice < 0.95: # [0.85 - 0.95] 10% 概率：走廊混响 (IR)
+            # 使用你测试过最好的 0.8/0.2 比例
+            dry = waveform_3d.clone()
+            wet = self.apply_ir(waveform_3d, sample_rate=self.sample_rate)
+            waveform_3d = 0.8 * dry + 0.2 * wet            
+        else: # [0.95 - 1.00] 5% 概率：极性翻转
+            waveform_3d = self.polarity_inversion(waveform_3d, sample_rate=self.sample_rate)
+        
+        #  [1, 1, time] -> [1, time]
+        waveform = waveform_3d.squeeze(0)
+
+        # 防止多次 augment 后振幅溢出，最后归一化
+        max_amp = waveform.abs().max()
+        if max_amp > 1.0:
+            waveform = waveform / max_amp
         
         return waveform
         
-    def _voice_stretch_or_compress(self, waveform: Tensor) -> Tensor:
-        speed_factor = random.uniform(0.6, 1.4) # (Speed Change: 0.6x - 1.4x)
+    def _stretch_or_compress(self, waveform: Tensor) -> Tensor:
+        speed_factor = random.uniform(0.80, 1.6) # (Speed Change: 0.85x - 1.4x)
         spec = torch.stft(
             waveform.squeeze(0),
             n_fft=400,
@@ -140,110 +213,93 @@ class CommonVoiceDataset(Dataset[BatchItem]):
         )
         
         # 时间拉伸（不改变音高）
-        stretch = TimeStretch(
-            hop_length=160,
-            n_freq=201,
-            fixed_rate=speed_factor
-        )
-        stretched_spec = stretch(spec)
+        stretched_spec = TimeStretch(hop_length=160, n_freq=spec.shape[-2], fixed_rate=speed_factor)(spec)
         
         # 转回波形
-        waveform_stretched = torch.istft(
-            stretched_spec,
-            n_fft=400,
-            hop_length=160,
-            window=torch.hann_window(400).to(waveform.device)
-        ).unsqueeze(0)
+        waveform_stretched = torch.istft(stretched_spec, n_fft=400, hop_length=160, window=torch.hann_window(400).to(waveform.device)).unsqueeze(0)
     
         return waveform_stretched
     
-    def _add_noise(self, waveform: Tensor, snr_db: float = None) -> Tensor:
-        if snr_db is None:
-            snr_db = random.uniform(15, 25)
+    def _time_mask_waveform(self, waveform: Tensor) -> Tensor:
+        audio_len = waveform.shape[1]
+        sr = self.sample_rate # 16000
         
-        signal_power = waveform.norm(p=2)
+        # 设置参数：单次遮盖最长 0.4 秒 (6400个点)
+        max_mask_time = 0.4
+        max_mask_samples = int(sr * max_mask_time)
         
-        snr_linear = 10 ** (snr_db / 10)
-        noise_power = signal_power / snr_linear
+        # 根据音频长度决定遮盖次数：
+        # 比如每 3 秒钟允许遮盖 1 次
+        num_masks = max(1, audio_len // (sr * 3)) 
         
-        # Generate Gaussian noise
-        noise = torch.randn_like(waveform) * noise_power / waveform.shape[1] ** 0.5
+        for _ in range(num_masks):
+            # 每次随机遮盖 0.1s 到 0.4s
+            current_mask_len = random.randint(int(sr * 0.1), max_mask_samples)
             
-        noisy_waveform: Tensor = waveform + noise
+            if audio_len > current_mask_len:
+                start_pos = random.randint(0, audio_len - current_mask_len)
                 
-        max_val = noisy_waveform.abs().max()
-        if max_val > 0:
-            noisy_waveform = noisy_waveform / max_val
+                # 填充微小噪音（模拟环境底噪）
+                noise = torch.randn(1, current_mask_len).to(waveform.device) * 0.002
+                waveform[:, start_pos : start_pos + current_mask_len] = noise
                 
-        return noisy_waveform
-    
-    def _augment_spec(self, mel_spec: Tensor) -> Tensor:
-        if not self.augment or random.random() > self.augment_prob:
-            return mel_spec
-        mel_spec = self.time_masking(mel_spec)
-        mel_spec = self.freq_masking(mel_spec)
-        return mel_spec
+        return waveform
     
     def __getitem__(self, index) -> BatchItem:
         row: TsvFormat = self.data.iloc[index]
         audio_path: Path = self.audio_dir / row['path']
-        # text: str = unicodedata.normalize('NFC', row['sentence'].strip()) 
-        text: str = normalize_extended_uyghur_characters(collapse_spaces(row['sentence'].strip()))
+        text: str = clean_input_text(row['sentence'].strip())
 
         waveform = self._load_audio(audio_path=audio_path)
         waveform = self._augment_waveform(waveform)
-        mel_spec = self._extract_features(waveform=waveform)
-        mel_spec = self._augment_spec(mel_spec=mel_spec)
+        waveform = waveform.squeeze(0)
 
         return BatchItem(
-            mel_spec=mel_spec,
+            waveform=waveform,
             target_ids=torch.tensor(self.tokenizer.encode(text), dtype=torch.long),
             target_text=text,
             audio_path=str(audio_path)
         )
     
 def collate_fn(items: List[BatchItem]) -> Batch:
-    max_mel_len = max(item['mel_spec'].shape[1] for item in items)
+    max_waveform_len = max(item['waveform'].shape[0] for item in items)
     max_target_len = max(len(item['target_ids']) for item in items)
 
     batch_size = len(items)
-    n_mels = items[0]['mel_spec'].shape[0]
 
-    mel_specs = torch.zeros(batch_size, n_mels, max_mel_len)
+    waveforms = torch.zeros(batch_size, max_waveform_len)
     targets = torch.zeros(batch_size, max_target_len, dtype=torch.long)
-    mel_lengths = torch.zeros(batch_size, dtype=torch.long)
+    waveform_lengths = torch.zeros(batch_size, dtype=torch.long)
     target_lengths = torch.zeros(batch_size, dtype=torch.long)
 
     target_texts = []
     audio_paths = []
-    
-
     for i, item in enumerate(items):
-        mel_len = item['mel_spec'].shape[1]
+        waveform_len = item['waveform'].shape[0]
         target_len = len(item['target_ids'])
 
-        mel_specs[i, :, :mel_len] = item['mel_spec']
+        waveforms[i, :waveform_len] = item['waveform']
         targets[i, :target_len] = item['target_ids']
-        mel_lengths[i] = mel_len
+        waveform_lengths[i] = waveform_len
         target_lengths[i] = target_len
 
         target_texts.append(item['target_text'])
         audio_paths.append(item['audio_path'])
 
     return Batch(
-        mel_specs=mel_specs,
+        waveforms=waveforms,
         targets=targets,
-        mel_lengths=mel_lengths,
+        waveform_lengths=waveform_lengths,
         target_lengths=target_lengths,
         target_texts=target_texts,
         audio_paths=audio_paths
     )
 
 
-def create_dataloader(tsv_path: Path, audio_dir: Path, tokenizer: ASRTokenizer, batch_size: int = 8, shuffle: bool = True, augment: bool = True) -> DataLoader:
-    dataset = CommonVoiceDataset(tsv_path=tsv_path, audio_dir=audio_dir, tokenizer=tokenizer, augment=augment)
+def create_dataloader(tsv_path: Path, audio_dir: Path, noise_dir: Path, corridor_noise_dir: Path, tokenizer: ASRTokenizer, batch_size: int = 8, shuffle: bool = True, augment: bool = True, augment_prob: float = 0.5) -> DataLoader:
+    dataset = CommonVoiceDataset(tsv_path=tsv_path, audio_dir=audio_dir, noise_dir=noise_dir, corridor_noise_dir=corridor_noise_dir, tokenizer=tokenizer, augment=augment, augment_prob=augment_prob)
 
-    return DataLoader(dataset=dataset, batch_size=batch_size, shuffle=shuffle, collate_fn=collate_fn, pin_memory=True, num_workers=8, prefetch_factor=8, persistent_workers=True)
+    return DataLoader(dataset=dataset, batch_size=batch_size, shuffle=shuffle, collate_fn=collate_fn, pin_memory=True, num_workers=8, prefetch_factor=8, persistent_workers=False)
 
 
 # ============ 测试代码 ============
@@ -268,9 +324,9 @@ if __name__ == "__main__":
     print("测试数据加载:")
     for batch in dataloader:
         batch: Batch
-        print(f"Mel specs shape: {batch['mel_specs'].shape}")
+        print(f"Waveform specs shape: {batch['targets'].shape}")
         print(f"Targets shape: {batch['targets'].shape}")
-        print(f"Mel lengths: {batch['mel_lengths']}")
+        print(f"Waveform lengths: {batch['waveform_lengths']}")
         print(f"Target lengths: {batch['target_lengths']}")
         print(f"Target texts: {batch['target_texts']}")
         print(f"Audio paths: {batch['audio_paths']}")

src/handle/audio_agement.ipynb

@@ -0,0 +1,129 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f6132018",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import random\n",
+    "import torchaudio\n",
+    "from torch import Tensor\n",
+    "from pathlib import Path\n",
+    "from IPython.display import Audio\n",
+    "from torch_audiomentations import Gain, PitchShift, LowPassFilter, HighPassFilter, ApplyImpulseResponse, Compose, BandPassFilter, PolarityInversion\n",
+    "workspace_dir = Path.cwd().parent.parent\n",
+    "sample_rate = 16000"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a238e4ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "transforms = {\n",
+    "    \"gain_up\": Gain(min_gain_in_db=4, max_gain_in_db=8, p=1.0, output_type='tensor'),\n",
+    "    \"gain_down\": Gain(min_gain_in_db=-15, max_gain_in_db=-8, p=1.0, output_type='tensor'),\n",
+    "    \"pitch_up\": PitchShift(min_transpose_semitones=1, max_transpose_semitones=4, p=1.0, sample_rate=sample_rate, output_type='tensor'),\n",
+    "    \"pitch_down\": PitchShift(min_transpose_semitones=-4, max_transpose_semitones=-1, p=1.0, sample_rate=sample_rate, output_type='tensor'),\n",
+    "    \"lowpass\": LowPassFilter(min_cutoff_freq=600, max_cutoff_freq=2000, p=1.0, output_type='tensor'),\n",
+    "    \"highpass\": HighPassFilter(min_cutoff_freq=800, max_cutoff_freq=2000, p=1.0, output_type='tensor')\n",
+    "}\n",
+    "\n",
+    "audio_path = workspace_dir / 'data/test/F001_001.wav'\n",
+    "audio_path = \"/mnt/train/audio/meshel_voice/01_separated/.data/Ataman/files/htdemucs_ft/3572399316_100010414/vocals.m4a\"\n",
+    "\n",
+    "waveform, sample_rate = torchaudio.load_with_torchcodec(audio_path)\n",
+    "print(waveform.shape)\n",
+    "if waveform.dim() == 2:\n",
+    "    waveform = waveform.unsqueeze(0)\n",
+    "\n",
+    "print(f\"原始音频: shape={waveform.shape}, sample_rate={sample_rate}\")\n",
+    "print('orginal')\n",
+    "display(Audio(waveform.squeeze(0), rate=sample_rate))\n",
+    "\n",
+    "noise_audio = workspace_dir / 'data/test/output.wav'\n",
+    "noise_audio = workspace_dir / 'data/corridor'\n",
+    "test_transform = LowPassFilter(min_cutoff_freq=800, max_cutoff_freq=2000, p=1.0, sample_rate=sample_rate, output_type='tensor')\n",
+    "out: Tensor = test_transform(waveform, sample_rate=sample_rate)\n",
+    "\n",
+    "max_amp = out.abs().max()\n",
+    "if max_amp > 1.0:\n",
+    "    print(max_amp)\n",
+    "    # out = out / max_amp\n",
+    "display(Audio(out.squeeze(0), rate=sample_rate))\n",
+    "# for name, transform in transforms.items():\n",
+    "#     out: Tensor = transform(waveform, sample_rate=sample_rate)\n",
+    "#     out.squeeze(0)\n",
+    "#     max_val = out.abs().max()\n",
+    "#     if max_val > 1.0:\n",
+    "#         print(f\"max_val: {max_val}\")\n",
+    "#         waveform_3d = waveform / max_val\n",
+    "#     print(f\"name: {name}, shepe: {out.shape}\")\n",
+    "#     display(Audio(out.squeeze(0), rate=sample_rate))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "aadb05aa",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.5\n"
+     ]
+    }
+   ],
+   "source": [
+    "import math\n",
+    "\n",
+    "final_prob = 0.5\n",
+    "warmup_epochs = 6\n",
+    "current_prob = 0.0\n",
+    "\n",
+    "def test_function(augment: float):\n",
+    "    print(augment)\n",
+    "# current_prob = final_prob * (1 - math.cos(math.pi * epoch / warmup_epochs)) / 2\n",
+    "# current_prob = final_prob * (1 - math.cos(math.pi * min(epoch, warmup_epochs) / warmup_epochs)) / 2\n",
+    "\n",
+    "for epoch in range(10):\n",
+    "    epoch = epoch + 1\n",
+    "    current_prob = final_prob * min(1.0, epoch / warmup_epochs)\n",
+    "\n",
+    "\n",
+    "epoch = 14\n",
+    "current_prob = final_prob * min(1.0, epoch / warmup_epochs)\n",
+    "# current_prob = final_prob * (epoch - 3) / (8 - 3)\n",
+    "print(current_prob)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "audio-model (3.11.12)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

src/handle/audio_analyze.py

@@ -0,0 +1,70 @@
+from pathlib import Path
+from tqdm import tqdm
+from mutagen.mp3 import MP3
+from mutagen import MutagenError
+import pandas as pd
+
+workspace_dir = Path(__file__).parent.parent.parent
+
+def format_duration(seconds):
+    """将秒数格式化为 时:分:秒 的格式"""
+    hours = int(seconds // 3600)
+    minutes = int((seconds % 3600) // 60)
+    secs = int(seconds % 60)
+    
+    if hours > 0:
+        return f"{hours}小时{minutes}分{secs}秒"
+    elif minutes > 0:
+        return f"{minutes}分{secs}秒"
+    else:
+        return f"{secs}秒"
+
+def get_mp3_duration(file_path: Path):
+    """获取单个MP3文件的时长（秒）"""
+    try:
+        audio = MP3(file_path)
+        return audio.info.length
+    except MutagenError as e:
+        print(f"错误：无法读取文件 {file_path} - {e}")
+        return None
+    except Exception as e:
+        print(f"错误：处理文件 {file_path} 时出错 - {e}")
+        return None
+
+def analyze_mp3_files(directory: Path, ):
+    """分析目录中的所有MP3文件"""
+    results = []
+    total_duration = 0
+    df = pd.read_csv(workspace_dir / '.data/ug/validated.tsv', sep='\t')
+
+    for _, row in tqdm(df.iterrows(), total=len(df), desc="anlayze audio"):
+        mp3_file: Path = workspace_dir / '.data/ug/clips'  / row['path']
+        duration = get_mp3_duration(mp3_file)
+        
+        if duration is not None:
+            total_duration += duration
+            duration_str = format_duration(duration)
+            file_size = mp3_file.stat().st_size / (1024 * 1024)  # 转换为MB
+            
+            result_line = f"{mp3_file.name:<50} {duration_str:>20} ({file_size:.2f} MB)"
+            results.append(result_line)
+        else:
+            error_line = f"{mp3_file.name:<50} {'读取失败':>20}"
+            print(error_line)
+            results.append(error_line)
+
+    mp3_files: list[Path] = []
+    for ext in ['*.mp3', '*.MP3']:
+            mp3_files.extend(directory.rglob(ext))
+    
+    print(f"tsv 找到 {len(results)} 个MP3文件\n")
+    print(f"找到 {len(mp3_files)} 个MP3文件\n")
+    print(f"\n总时长: {format_duration(total_duration)}")
+    print(f"总时长(秒): {total_duration:.2f} 秒")
+    print(f"总时长(分钟): {total_duration/60:.2f} 分钟")
+    print(f"总时长(小时): {total_duration/3600:.2f} 小时")
+    print(f"文件总数: {len(mp3_files)}")
+
+
+audio_directory = Path(workspace_dir / '.data/ug/clips')
+analyze_mp3_files(directory=audio_directory)

src/handle/export_model_state_dict.py

@@ -1,14 +1,53 @@
 
+import json
 from pathlib import Path
 
 import torch
 
 device = "cuda:0"
-workspace_dir = Path(__file__).parent.parent
+workspace_dir = Path(__file__).parent.parent.parent
 
-input_checkpoint = workspace_dir.joinpath('.checkpoints/checkpoint_step_9500.pt')
-output_checkpoint = workspace_dir.joinpath('.checkpoints/checkpoint_step.pt')
+input_checkpoint = workspace_dir.joinpath('.checkpoints/base_model/checkpoint_epoch_26.pt')
+output_checkpoint = workspace_dir.joinpath('.checkpoints/retrain.pt')
 
 checkpoint = torch.load(input_checkpoint, map_location=device)
-torch.save(checkpoint['model_state_dict'], output_checkpoint)
 
+checkpoint = {
+    'model_state_dict': checkpoint['model_state_dict'],
+    # 'optimizer_state_dict': checkpoint['optimizer_state_dict'],
+}
+torch.save(checkpoint, output_checkpoint)
+
+# torch.save(checkpoint['model_state_dict'], output_checkpoint)
+
+
+def query_model_parameter():
+    base_dir = workspace_dir / '.checkpoints/base_model'
+    checkpoints_info = []
+
+    for ckpt_path in sorted(base_dir.glob('checkpoint_epoch_*.pt'), key=lambda p: int(p.stem.split('_')[-1])):
+        ckpt = torch.load(ckpt_path, weights_only=False, map_location='cuda:1')
+        info = {
+            "file_name": ckpt_path.name,
+            "epoch": ckpt.get("epoch", "N/A"),
+            "train_loss": ckpt.get("train_loss", "N/A"),
+            "val_loss": ckpt.get("val_loss", "N/A"),
+            "cer": ckpt.get("cer", "N/A"),
+            "wer": ckpt.get("wer", "N/A"),
+            "has_scheduler": "scheduler_state_dict" in ckpt
+        }
+        checkpoints_info.append(info)
+        print(f'{ckpt_path.name}:')
+        print(f'  Epoch: {ckpt.get("epoch", "N/A")}')
+        print(f'  Train Loss: {ckpt.get("train_loss", "N/A")}')
+        print(f'  Val Loss: {ckpt.get("val_loss", "N/A")}')
+        print(f'  CER: {ckpt.get("cer", "N/A")}')
+        print(f'  WER: {ckpt.get("wer", "N/A")}')
+        print(f'  Has scheduler: {"scheduler_state_dict" in ckpt}')
+        print()
+
+    output_path = base_dir / 'checkpoints_summary.json'
+    with open(output_path, 'w', encoding='utf-8') as f:
+        json.dump(checkpoints_info, f, ensure_ascii=False, indent=2)
+
+# query_model_parameter()

src/handle/export_new_tsv.py

@@ -0,0 +1,37 @@
+from pathlib import Path
+
+import pandas as pd
+workspace_dir = Path(__file__).parent.parent.parent
+
+# 读取你合并后的总表 (253,430条)
+df = pd.read_csv(workspace_dir / ".data/ug/validated.tsv", sep='\t')
+
+# 1. 获取所有唯一的说话人
+all_speakers = df['client_id'].unique()
+
+# 2. 随机打乱说话人顺序
+import random
+random.seed(42) # 固定随机种子，保证实验可重复
+random.shuffle(all_speakers)
+
+# 3. 挑选验证集说话人，直到录音总数达到 ~8000 条
+val_indices = []
+val_count = 0
+target_val_size = 8000
+
+for speaker in all_speakers:
+    speaker_data = df[df['client_id'] == speaker]
+    val_indices.extend(speaker_data.index.tolist())
+    val_count += len(speaker_data)
+    if val_count >= target_val_size:
+        break
+
+# 4. 划分文件
+df_val = df.loc[val_indices]
+df_train = df.drop(val_indices)
+
+print(f"训练集条数: {len(df_train)}")
+print(f"验证集条数: {len(df_val)}")
+
+df_train.to_csv(workspace_dir / ".data/ug/train_new.tsv", sep='\t', index=False)
+df_val.to_csv(workspace_dir / ".data/ug/val_new.tsv", sep='\t', index=False)

src/handle/export_tokens.py

@@ -0,0 +1,38 @@
+
+from pathlib import Path
+import sys
+
+from tqdm import tqdm
+
+from text_normalizer import collapse_spaces
+
+
+
+workspace_dir = Path(__file__).parent.parent.parent
+sys.path.append(str(workspace_dir.joinpath('src')))
+# sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from handle.text_handle import process_text
+from tokenizer import ASRTokenizer
+
+# text = "ئىكەنلىكىنى، بۈگۈنكىسى 20 يىللىق ساقچىلىق جەريانىدا تۇنجى"
+# text = "	يېزىدىكى كەڭ، ئازادە ئۆي، باغلىرىنى تاشلاپ، خەقنىڭ ھويلىسىدا قورۇنۇپ-ئەيمىنىپ يەر دەسسەپ يۈردى.	"
+# text = "بۇ يىللىق ئەمگەكچىلەر بايرىمىدا، 1-مايدىن 5-مايغىچە جەمئىي بەش كۈن دەم ئېلىشقا قويۇپ بېرىلىدۇ. 9-ماي (شەنبە) نورمال خىزمەت قىلىنىدۇ. شۇنىڭ بىلەن بىر ۋاقىتتا، ئۈرۈمچى شەھىرى تىيانشان رايونى، سايباغ رايونى، داۋانچىڭ رايونى، ئۈرۈمچى ناھىيەسىدىكى ئوتتۇرا، باشلانغۇچ مەكتەپلەر 29-ئاپرېلدىن 30-ئاپرېلغىچە ئەتىيازلىق دەم ئېلىشقا قويۇپ بېرىدۇ؛ سانجى ئوبلاستىدىكى ئوتتۇرا، باشلانغۇچ مەكتەپلەرنىڭ ئەتىيازلىق دەم ئېلىشى ئۈچ كۈن بولۇپ، بۇنىڭ ئىچىدە ئىككى كۈن 29-، 30-ئاپرېلغا ئورۇنلاشتۇرۇلىدۇ، قالغان بىر كۈن 1-ئىيۇنغا ئورۇنلاشتۇرۇلىدۇ، قۇربان ھېيتلىق دەم ئېلىش بىلەن بىرلەشتۈرۈلۈپ، ئۇدا ئالتە كۈن دەم ئېلىنىدۇ."
+# text = "ئەڭ يېڭى دەم ئېلىشقا قويۇپ بېرىش ئۇقتۇرۇشى! تەقەززالىق بىلەن كۈتكەن يەنە بىر دەم ئېلىش كېلەي دەپ قالدى! گوۋۇيۈەن بەنگۇڭتىڭىنىڭ «2025-يىللىق قىسمەن بايرام، دەم ئېلىش كۈنلىرىنى ئورۇنلاشتۇرۇش توغرىسىدىكى ئۇقتۇرۇشى»غا ئاساسەن، دۈەنۋۇ بايرىمىلىق دەم ئېلىشقا قويۇپ بېرىش ئورۇنلاشتۇرۇلۇشى تۆۋەندىكىچە: 5-ئاينىڭ 31-كۈنى (شەنبە)دىن 6-ئاينىڭ 2-كۈنىگىچە جەمئىي ئۈچ كۈن دەم ئېلىشقا قويۇپ بېرىلىدۇ! بۇ قېتىمقى دۈەنۋۇ بايرىمىلىق دەم ئېلىش ۋاقتى تەڭشەلمەيدۇ!"
+# text = "مەن شۇ چاغدا چۈشۈمدىمۇ كۆرۈپ باقمىغان مۇنچىۋالا جىق قېرىنداشلىرىم، جىگەرلىرىمنىڭ بارلىقىدىن سۆيۈندۈم."
+# text = "ئامېرىكا جاھان گىرلىكىگە قارشى تۇرۇپ، چاۋشەنگە ياردەم بىرىش ئۇرۇشىنىڭ ئۇلۇغ غەلبىسى، جۇڭگو خەلقى ئورۇندىن دەس تۇرغاندىنكىن دۇنيانىڭ شەرقىدە قەد       كۆتۈرگەنلىكىنىڭ خىتاپنامىس"
+
+tokenizer = ASRTokenizer(vocab_path=workspace_dir / 'config/asr_vocab.json')
+
+# result = export_syllabize(text)
+# result = process_text(text)
+# print(f"Original: {text}")
+# print(f"Syllables: {result}")
+
+with open('/mnt/train/nmt/data/temp/uig_Arab.txt', 'r', encoding='utf-8') as f:
+    with open('/mnt/train/nmt/data/temp/uig_Arab_tokenized.txt', 'w', encoding='utf-8') as w:
+        lines = f.readlines()
+        for line in tqdm(lines):
+            w.write(collapse_spaces(" ".join([tokenizer.decode([t]).replace(" ", "<SPACE>") for t in tokenizer.encode(line.strip())])) + '\n')
+
+# ids = tokenizer.encode(text=text)
+# print(' '.join(tokenizer.decode([id]) for id in ids))

src/handle/test.py

@@ -11,11 +11,12 @@ from tqdm import tqdm
 workspace_dir = Path(__file__).parent.parent.parent
 sys.path.append(str(workspace_dir.joinpath('src')))
 # sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from handle.text_normalizer import clean_input_text
 from handle.text_handle import process_text
 from tokenizer import ASRTokenizer
 
 # 读取 TSV
-# df = pd.read_csv(workspace_dir / '.data/ug/train.tsv', sep='\t')
+# df = pd.read_csv(workspace_dir / '.data/ug/validated.tsv', sep='\t')
 
 # # 计算每个音频的时长（秒）
 # durations = []
@@ -36,12 +37,13 @@ from tokenizer import ASRTokenizer
 # print(df['duration'].describe())
 # print(f"超过20秒的样本: {(df['duration'] > 20).sum()}")
 
-# 保存结果（可选）
+# # 保存结果（可选）
 # df.to_csv('data/audio/train_with_duration.tsv', sep='\t', index=False)
 
 # audio_path = workspace_dir / '.data/ug/clips/common_voice_ug_40252722.mp3'
 # info = torchaudio.info(audio_path)
 # print("info:", info)
+
 import pandas as pd
 import torch
 import torchaudio
@@ -196,8 +198,8 @@ text = "\" 15 يىل بۇرۇن مەن بىلەن سەي چۇڭشىن (ئال
 # text = "يۆ جيەنتاۋ يېقىنقى بىر مەزگىلدە، خىزمەتداشلىرى بىلەن نۇرغۇن قىيىنچىلىققا ئۇچرىغان شوپۇرغا ياردەم قىلغانلىقىنى، شۇنداقلا يېمەكلىك ۋە سۇ يەتكۈزۈپ بەرگەنلىكىنى، ئەمما ئاياغ سوۋغا قىلىشى تۇنجى قېتىم ئىكەنلىكىنى، بۈگۈنكىسى 20 يىللىق ساقچىلىق جەريانىدا تۇنجى قېتىم شوپۇرغا ئاياغ سوۋغا قىلىشى ئىكەنلىكىنى ئېيتتى."
 text = "يۆ جۇڭمىڭ مۇنداق دېدى: 2019- يىلى 12-ئايدا، مەملىكەتلىك خەلق قۇرۇلتىيى دائىمىي كومىتېتىنىڭ 44- قېتىملىق كومىتېت باشلىقلىرى يىغىنى مەملىكەتلىك خەلق قۇرۇلتىيى دائىمىي كومىتېتىنىڭ 2020-يىللىق قانۇن چىقىرىش خىزمىتى پىلانىنى پىرىنسىپ جەھەتتىن ماقۇللىدى، خىزمەت تەرتىپى بويىچە، 13-نۆۋەتلىك مەملىكەتلىك خەلق قۇرۇلتىيى 3-يىغىنىنىڭ روھى ۋە ۋەكىللەرنىڭ تەكلىپ-تەۋسىيەلىرىگە ئاساسەن پىلاننى تەڭشەش كېرەك. بۇ يىل 6-ئاينىڭ 1-كۈنى، 58-قېتىملىق كومىتېت باشلىقلىرى يىغىنى تەڭشەلگەندىن كېيىنكى يىللىق قانۇن چىقىرىش خىزمىتى پىلانىنى قاراپ چىقىپ ماقۇللىدى."
 text = "	ئاشقازان-ئۈچەينىڭ لۆمۈلدىشىنى ئىلگىرى سۈرىدىغان دورىنى تاماقتىن بۇرۇن ئىستېمال قىلىش كېرەك."
-# text = "مەن مەكتەپكە باردىم"
-# text = "غەرىپئەللىرى"
+text = "مەن مەكتەپكە باردىم"
+text = "غەرىپئەللىرى"
 # text = "ئىكەنلىكىنى، بۈگۈنكىسى 20 يىللىق ساقچىلىق جەريانىدا تۇنجى"
 # text = "	يېزىدىكى كەڭ، ئازادە ئۆي، باغلىرىنى تاشلاپ، خەقنىڭ ھويلىسىدا قورۇنۇپ-ئەيمىنىپ يەر دەسسەپ يۈردى.	"
 # text = "بۇ يىللىق ئەمگەكچىلەر بايرىمىدا، 1-مايدىن 5-مايغىچە جەمئىي بەش كۈن دەم ئېلىشقا قويۇپ بېرىلىدۇ. 9-ماي (شەنبە) نورمال خىزمەت قىلىنىدۇ. شۇنىڭ بىلەن بىر ۋاقىتتا، ئۈرۈمچى شەھىرى تىيانشان رايونى، سايباغ رايونى، داۋانچىڭ رايونى، ئۈرۈمچى ناھىيەسىدىكى ئوتتۇرا، باشلانغۇچ مەكتەپلەر 29-ئاپرېلدىن 30-ئاپرېلغىچە ئەتىيازلىق دەم ئېلىشقا قويۇپ بېرىدۇ؛ سانجى ئوبلاستىدىكى ئوتتۇرا، باشلانغۇچ مەكتەپلەرنىڭ ئەتىيازلىق دەم ئېلىشى ئۈچ كۈن بولۇپ، بۇنىڭ ئىچىدە ئىككى كۈن 29-، 30-ئاپرېلغا ئورۇنلاشتۇرۇلىدۇ، قالغان بىر كۈن 1-ئىيۇنغا ئورۇنلاشتۇرۇلىدۇ، قۇربان ھېيتلىق دەم ئېلىش بىلەن بىرلەشتۈرۈلۈپ، ئۇدا ئالتە كۈن دەم ئېلىنىدۇ."
@@ -207,14 +209,32 @@ text = "	ئاشقازان-ئۈچەينىڭ لۆمۈلدىشىنى ئىلگىرى
 
 
 # result = export_syllabize(text)
-result = process_text(text)
-print(f"Original: {text}")
-print(f"Syllables: {result}")
+# result = process_text(text)
+# print(f"Original: {text}")
+# print(f"Syllables: {result}")
 
 
 tokenizer = ASRTokenizer(vocab_path=workspace_dir / 'config/asr_vocab.json')
 
-print(text)
-ids = tokenizer.encode(text=text)
-# print(ids)
-print('|'.join(tokenizer.decode([id]) for id in ids))
+def static_token(tsv_path: Path):
+    df = pd.read_csv(tsv_path, sep='\t')
+    unk_samples = []
+    # for _, row in tqdm(df.iterrows(), total=len(df), desc="anlayze token"):
+    for sentence in tqdm(df['sentence'], total=len(df), desc="analyze token"):
+        text = clean_input_text(sentence.strip())
+        encoded = tokenizer.encode(text=text)
+        decoded = tokenizer.decode(encoded)
+        if "<UNK>" in decoded:
+            unk_samples.append({
+                # 'original': sentence.strip(),
+                'cleaned': text,
+                'decoded': decoded,
+                # 'encoded': encoded
+            })
+    
+    print(f"UNK samples: {len(unk_samples)} / {len(df)}")
+    return unk_samples
+
+tsv_path = workspace_dir / '.data/ug/train_new.tsv'
+unk_samples = static_token(tsv_path=tsv_path)
+# print(unk_samples)

src/handle/text_handle.py

@@ -1,5 +1,10 @@
 
-from .text_normalizer import UYGHUR_LETTERS, clean_input_text
+from pathlib import Path
+
+import pandas as pd
+from tqdm import tqdm
+
+from .text_normalizer import UYGHUR_LETTERS, clean_input_text, collapse_spaces, normalize_extended_uyghur_characters
 
 # def uighur_syllabize(text: str):
 #     # Uyghur Vowels
@@ -163,15 +168,13 @@ def uighur_syllabize(text: str):
 
 text = "	ھەر قانداق ئىشتا كىشىلەر بىلەن كېڭىشىش كېرەك. لېكىن كۆڭۈل تارتقان ئىشنى قىلىۋېرىش كېرەك."
 text = "\" 15 يىل بۇرۇن مەن بىلەن سەي چۇڭشىن (ئالى بابانىڭ قۇرغۇچىسىدىن بىرى) ئامېرىكىغا بېرىپ 30 نەچچە مەبلەغ سالغۇچى شىركەتلەر بىلەن كۆرۈشكىنىمىزدە ئۇلار بىزنى رەت قىلىپ ئىشىك سىرتىدا قالدۇرغاندى. ھېچكىم بىزگە ۋە كەلگۈسىمىزگە ئىشەنمىگەن ئىدى، ھېچكىممۇ بىزنىڭ ھازىر 300 مىليارد سودىنى تاماملىيالايدىغانلىقىمىزنى ئويلاپ خىيالىغىمۇ كەلتۈرمىگەن ئىدى.\" ئالى بابانىنىڭ ئورگىنى تەرىپىدىن ئىشلەنگەن ئىگىلىك تىكلەش ھۆججەتلىك فىلىمى \" بۇ چۈش ئەمەس\" نىڭ باش قىسمىدا مۇنداق بىر داڭلىق سۆز چىقىدۇ:\" مەن تاغدىن ئۆتكەن ۋاقتىمدا تاغ ماڭا گەپ قىلمىدى، مەن دېڭىزنى كېچىپ ئۆتكىنىمدە دېڭىز ماڭا گەپ قىلمىدى.\" بۇ فىلىمنىڭ قوشۇمچە ئىسمى بولسا \" مايۈن ۋە ئۇنىڭ مەڭگۈلۈك ' ياش ئالى'سى\" بولۇپ، ھەرخىل خەتەر ۋە قىيىنلىقنى بىرمۇ بىر يەڭگەن مايۈن ۋە ئۇنىڭ ئالى بابا قوشۇنىدىكى ھەمكارلاشقۇچىلىرىنىڭ قەيسەر كەچمىشى جانلىق بايان قىلىنغان."
-text = "يۆ جيەنتاۋ يېقىنقى بىر مەزگىلدە، خىزمەتداشلىرى بىلەن نۇرغۇن قىيىنچىلىققا ئۇچرىغان شوپۇرغا ياردەم قىلغانلىقىنى، شۇنداقلا يېمەكلىك ۋە سۇ يەتكۈزۈپ بەرگەنلىكىنى، ئەمما ئاياغ سوۋغا قىلىشى تۇنجى قېتىم ئىكەنلىكىنى، بۈگۈنكىسى 20 يىللىق ساقچىلىق جەريانىدا تۇنجى قېتىم شوپۇرغا ئاياغ سوۋغا قىلىشى ئىكەنلىكىنى ئېيتتى."
-text = "يۆ جۇڭمىڭ مۇنداق دېدى: 2019- يىلى 12-ئايدا، مەملىكەتلىك خەلق قۇرۇلتىيى دائىمىي كومىتېتىنىڭ 44- قېتىملىق كومىتېت باشلىقلىرى يىغىنى مەملىكەتلىك خەلق قۇرۇلتىيى دائىمىي كومىتېتىنىڭ 2020-يىللىق قانۇن چىقىرىش خىزمىتى پىلانىنى پىرىنسىپ جەھەتتىن ماقۇللىدى، خىزمەت تەرتىپى بويىچە، 13-نۆۋەتلىك مەملىكەتلىك خەلق قۇرۇلتىيى 3-يىغىنىنىڭ روھى ۋە ۋەكىللەرنىڭ تەكلىپ-تەۋسىيەلىرىگە ئاساسەن پىلاننى تەڭشەش كېرەك. بۇ يىل 6-ئاينىڭ 1-كۈنى، 58-قېتىملىق كومىتېت باشلىقلىرى يىغىنى تەڭشەلگەندىن كېيىنكى يىللىق قانۇن چىقىرىش خىزمىتى پىلانىنى قاراپ چىقىپ ماقۇللىدى."
-text = "مەن مەكتەپكە باردىم"
+# text = "شۇڭا ئۇ «ئورمان دوختۇرى» دەپ ئاتالغان."
+# text = "يۆ جيەنتاۋ يېقىنقى بىر مەزگىلدە، خىزمەتداشلىرى بىلەن نۇرغۇن قىيىنچىلىققا ئۇچرىغان شوپۇرغا ياردەم قىلغانلىقىنى، شۇنداقلا يېمەكلىك ۋە سۇ يەتكۈزۈپ بەرگەنلىكىنى، ئەمما ئاياغ سوۋغا قىلىشى تۇنجى قېتىم ئىكەنلىكىنى، بۈگۈنكىسى 20 يىللىق ساقچىلىق جەريانىدا تۇنجى قېتىم شوپۇرغا ئاياغ سوۋغا قىلىشى ئىكەنلىكىنى ئېيتتى."
+# text = "يۆ جۇڭمىڭ مۇنداق دېدى: 2019- يىلى 12-ئايدا، مەملىكەتلىك خەلق قۇرۇلتىيى دائىمىي كومىتېتىنىڭ 44- قېتىملىق كومىتېت باشلىقلىرى يىغىنى مەملىكەتلىك خەلق قۇرۇلتىيى دائىمىي كومىتېتىنىڭ 2020-يىللىق قانۇن چىقىرىش خىزمىتى پىلانىنى پىرىنسىپ جەھەتتىن ماقۇللىدى، خىزمەت تەرتىپى بويىچە، 13-نۆۋەتلىك مەملىكەتلىك خەلق قۇرۇلتىيى 3-يىغىنىنىڭ روھى ۋە ۋەكىللەرنىڭ تەكلىپ-تەۋسىيەلىرىگە ئاساسەن پىلاننى تەڭشەش كېرەك. بۇ يىل 6-ئاينىڭ 1-كۈنى، 58-قېتىملىق كومىتېت باشلىقلىرى يىغىنى تەڭشەلگەندىن كېيىنكى يىللىق قانۇن چىقىرىش خىزمىتى پىلانىنى قاراپ چىقىپ ماقۇللىدى."
+# text = "مەن مەكتەپكە باردىم"
 
-# text = normalize_extended_uyghur_characters(text=text)
-# print(clean_uyghur(text=text))
 
 def process_text(text: str) -> list[str]:
-    text = clean_input_text(text=text)
     result = []
     current_word_chars = []
     

src/handle/text_normalizer.py

@@ -122,5 +122,5 @@ def clean_input_text(text: str) -> str:
   text = collapse_spaces(text)
   text = clean_http_links(text)
   text = normalize_extended_uyghur_characters(text)
-  text = clean_unknown_symbols(text)
+  # text = clean_unknown_symbols(text)
   return text

src/inference.py

@@ -1,58 +1,37 @@
-import random
-
-import librosa
 import torch
 import torchaudio
 from torch import Tensor, no_grad, device
-from torchaudio.transforms import MelSpectrogram, AmplitudeToDB, Resample, TimeStretch
+from torchaudio.transforms import Resample
 from pathlib import Path
-import torchaudio.functional as F
-
+from typing import TypedDict
+from silero_vad import load_silero_vad, get_speech_timestamps
 from tokenizer import ASRTokenizer
 from model import ASRModel
 
 CONFIG = {
     # 模型配置
-    'input_dim': 640,
+    'input_dim': 256,
     'num_heads': 8,
     'ffn_dim': 2048,
     'num_layers': 8,
     'dropout': 0.1,
 }
 
-class ASRInference:
-    def __init__(self, model_path: Path, vocab_path: Path, device: device, augment: bool = True, augment_prob: float = 0.5) -> None:
-        self.device = device
-        self.augment: bool = augment
-        self.augment_prob: float = augment_prob
-        self.tokenizer = ASRTokenizer(vocab_path=vocab_path)
-        self.model = ASRModel(
-            vocab_size=self.tokenizer.vocab_size(),
-            input_dim=CONFIG['input_dim'],
-            num_heads=CONFIG['num_heads'],
-            ffn_dim=CONFIG['ffn_dim'],
-            num_layers=CONFIG['num_layers'],
-            dropout=CONFIG['dropout'],
-        ).to(device)
+class TimestampsType(TypedDict):
+    start: int
+    end: int
 
+class ASRInference:
+    def __init__(self, model_path: Path, vocab_path: Path, device: device, sample_rate: int = 16000) -> None:
+        self.device = device
+        self.sample_rate = sample_rate
+        self.tokenizer = ASRTokenizer(vocab_path=vocab_path)
+        self.model = ASRModel(vocab_size=self.tokenizer.vocab_size(), **CONFIG).to(device=device)
         self.model.load_state_dict(torch.load(model_path, map_location=device)['model_state_dict'])
         self.model.eval()
 
         print(f"params params: {self.model.get_num_params():,}",)
 
-        self.sample_rate = 16000
-        self.mel_transform = MelSpectrogram(
-            sample_rate=self.sample_rate,
-            n_fft=400,
-            win_length=400,
-            hop_length=160,
-            n_mels=80,
-            f_min=0,
-            f_max=8000,
-            power=2.0,
-        )
-        self.amplitude_to_db = AmplitudeToDB()
-
     def _load_audio(self, audio_path: Path)  -> Tensor:
         waveform, sample_rate = torchaudio.load_with_torchcodec(audio_path)
 
@@ -65,87 +44,12 @@ class ASRInference:
         waveform = waveform / (waveform.abs().max() + 1e-8)
         return waveform
     
-    def _extract_features(self, waveform: Tensor) -> Tensor:
-        mel_spec: Tensor = self.mel_transform(waveform)
-        log_mel_spec: Tensor = self.amplitude_to_db(mel_spec)
-        return log_mel_spec.squeeze(0) # [n_mels, time]
-    
-    def _augment_waveform(self, waveform: Tensor) -> Tensor:
-        if not self.augment or random.random() > self.augment_prob:
-            return waveform
-        
-        # 1. voice Stretch/Compress 
-        if random.random() < 0.5:
-            waveform = self._voice_stretch_or_compress(waveform=waveform)
-
-        if random.random() < 0.3:
-            waveform = self._drop_frames(waveform)
-
-        if random.random() < 0.4:
-            waveform = self._add_noise(waveform)
-        
-        return waveform
-    
-    def _voice_stretch_or_compress(self, waveform: Tensor) -> Tensor:
-        speed_factor = random.uniform(0.6, 1.4) # (Speed Change: 0.6x - 1.4x)
-        spec = torch.stft(
-            waveform.squeeze(0),
-            n_fft=400,
-            hop_length=160,
-            window=torch.hann_window(400).to(waveform.device),
-            return_complex=True
-        )
-        
-        # 时间拉伸（不改变音高）
-        stretch = TimeStretch(
-            hop_length=160,
-            n_freq=201,
-            fixed_rate=speed_factor
-        )
-        stretched_spec = stretch(spec)
-        
-        # 转回波形
-        waveform_stretched = torch.istft(
-            stretched_spec,
-            n_fft=400,
-            hop_length=160,
-            window=torch.hann_window(400).to(waveform.device)
-        ).unsqueeze(0)
-
-        return waveform_stretched
-
-    def _drop_frames(self, waveform: Tensor) -> Tensor:
-        audio_len = waveform.shape[1]
-        drop_ratio = random.uniform(0.05, 0.15)
-        drop_len = int(audio_len * drop_ratio)
-
-        if audio_len > drop_len:
-            start_pos = random.randint(0, audio_len - drop_len)
-            # clean
-            waveform = torch.cat([waveform[:, :start_pos], waveform[:, start_pos + drop_len:]], dim=1)
-
-        return waveform
-    
-    def _add_noise(self, waveform: Tensor) -> Tensor:
-        snr_db = random.uniform(10, 20)
-        signal_power = torch.mean(waveform ** 2)
-        
-        snr_linear = 10 ** (snr_db / 10)
-        noise_power = signal_power / snr_linear
-        
-        noise = torch.randn_like(waveform) * torch.sqrt(noise_power)
-        return waveform + noise
-    
-    def transcribe(self, audio_path: Path) -> str:
-        waveform = self._load_audio(audio_path=audio_path)
-        waveform = self._augment_waveform(waveform=waveform)
-        mel_spec = self._extract_features(waveform=waveform)
-
-        mel_spec = mel_spec.unsqueeze(0).to(self.device) # [1, n_mels, time]
-        mel_length = torch.tensor([mel_spec.shape[2]], dtype=torch.long, device=self.device)
+    def transcribe(self, waveform: Tensor) -> str:
+        waveform = waveform.to(device=self.device) # [1, time]
+        waveform_length = torch.tensor([waveform.shape[1]], dtype=torch.long, device=self.device)
 
         with no_grad():
-            log_probs, _ = self.model(mel_specs=mel_spec, mel_lengths=mel_length) # [1, T, vocab]
+            log_probs, _ = self.model(waveforms=waveform, waveform_lengths=waveform_length) # [1, T, vocab]
 
         text = self.tokenizer.ctc_greedy_decode(log_probs=log_probs[0])
         return text
@@ -154,30 +58,67 @@ class ASRInference:
         results = []
 
         for audio_path in audio_paths:
-            text = self.transcribe(audio_path=audio_path)
+            waveform = self._load_audio(audio_path=audio_path)
+            text = self.transcribe(waveform=waveform)
             results.append(text)
 
         return results
     
+    def create(self, audio_path: Path, threshold_ms: int = 20000):
+        def merge_timestamps(timestamps: int, threshold_ms: int, sample_rate: int):
+            if not timestamps:
+                return []
+            threshold_samples = (threshold_ms / 1000) * sample_rate
+            merged = []
+            curr_start = timestamps[0]['start']
+            curr_end = timestamps[0]['end']
+            
+            for i in range(1, len(timestamps)):
+                # 如果当前积攒的长度不到 2 秒，就一直合并到当前的 end 上
+                if (curr_end - curr_start) < threshold_samples:
+                    curr_end = timestamps[i]['end']
+                else:
+                    merged.append({'start': curr_start, 'end': curr_end})
+                    curr_start = timestamps[i]['start']
+                    curr_end = timestamps[i]['end']
+            merged.append({'start': curr_start, 'end': curr_end})
+            return merged
+
+        vad_model = load_silero_vad(onnx=False)
+        waveform = self._load_audio(audio_path=audio_path)
+        speech_timestamps: list[TimestampsType] = get_speech_timestamps(
+            waveform, 
+            vad_model, 
+            sampling_rate=self.sample_rate,
+            threshold=0.5,  # 可以根据需要调整阈值
+            min_speech_duration_ms=100, # 最小语音持续时间，防止短噪音被误判
+            min_silence_duration_ms=200, # 最小静音间隔，用于分割语音块
+            speech_pad_ms=100, # 在语音块前后添加的填充时间
+        )
+        final_timestamps = merge_timestamps(timestamps=speech_timestamps, threshold_ms=threshold_ms, sample_rate=self.sample_rate)
+        for ts in final_timestamps:
+            ts: TimestampsType
+            start_sample = int(ts['start'])
+            end_sample = int(ts['end'])
+
+            segment_waveform = waveform[:, start_sample:end_sample]
+
+            segment_text = self.transcribe(waveform=segment_waveform)
+            print(segment_text, end=" ", flush=True)
+        print('\n')
 
 def main():
     workspace_dir = Path(__file__).parent.parent
-    device = torch.device('cuda:0')
+    device = torch.device('cuda:1')
 
-    # checkpoint = sorted(workspace_dir.glob('.checkpoints/checkpoint_epoch_*.pt'), key=lambda p: int(p.stem.split('_')[1]))[-1]
-    checkpoint = workspace_dir / ".checkpoints/checkpoint_step_9500.pt"
-    print(f"Load Checkpoint: {checkpoint}")
-
-    inference = ASRInference(model_path=checkpoint, vocab_path=workspace_dir / 'config/uig_vocab.json' , device=device)
+    checkpoint = workspace_dir / ".checkpoints/best_wer_model.pt"
+    inference = ASRInference(model_path=checkpoint, vocab_path=workspace_dir / 'config/asr_vocab.json' , device=device)
 
     audio_path = workspace_dir / 'data/test/F001_001.wav'
-    print(f"\n转录音频: {audio_path}")
-    text = inference.transcribe(audio_path=audio_path)
-    print(f"\n识别结果: {text}")
+    waveform = inference._load_audio(audio_path=audio_path)
+    text = inference.transcribe(waveform=waveform)
+    print("transcribe:", text)
+    inference.create(audio_path=audio_path)
 
 if __name__ == "__main__":
     main()
-# workspace_dir = Path(__file__).parent.parent
-# checkpoint = sorted(workspace_dir.glob('.checkpoints/checkpoint_step_*.pt'), key=lambda p: int(p.stem.split('_')[-1]))[-1]
-
-# print(checkpoint)

src/model.py

@@ -1,36 +1,77 @@
-from torch.nn import Conv2d, Module, ReLU, Linear, functional
+from torch.nn import Module, Linear, functional, GELU, Conv1d, GroupNorm, ModuleList
 from torch import Tensor
 from torchaudio.models import Conformer
 
-
-class ASRModel(Module):
-    def __init__(self, vocab_size: int, input_dim: int = 640, num_heads: int = 8, ffn_dim: int = 2048, num_layers: int = 6, dropout: float = 0.1) -> None:
+class WaveformFilter(Module):
+    def __init__(self):
         super().__init__()
         
-        self.conv1 = Conv2d(in_channels=1, out_channels=16, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
-        self.conv2 = Conv2d(in_channels=16, out_channels=32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
-        self.conv3 = Conv2d(in_channels=32, out_channels=32, kernel_size=(3, 3), stride=(2, 1), padding=(1, 1))
-        self.proj = Linear(in_features=1280, out_features=640)
-        self.relu = ReLU()
+        self.filters = ModuleList([
+            Conv1d(in_channels=1, out_channels=512, kernel_size=10, stride=5),
+            GroupNorm(num_channels=512, num_groups=32),
+            GELU(),
+            Conv1d(in_channels=512, out_channels=512, kernel_size=3, stride=2),
+            GroupNorm(num_channels=512, num_groups=32),
+            GELU(),
+            Conv1d(in_channels=512, out_channels=512, kernel_size=3, stride=2),
+            GroupNorm(num_channels=512, num_groups=32),
+            GELU(),
+            Conv1d(in_channels=512, out_channels=512, kernel_size=3, stride=2),
+            GroupNorm(num_channels=512, num_groups=32),
+            GELU(),
+            Conv1d(in_channels=512, out_channels=512, kernel_size=3, stride=2),
+            GroupNorm(num_channels=512, num_groups=32),
+            GELU(),
+            Conv1d(in_channels=512, out_channels=512, kernel_size=2, stride=2),
+            GroupNorm(num_channels=512, num_groups=32),
+            GELU(),
+            Conv1d(in_channels=512, out_channels=512, kernel_size=2, stride=2),
+            GroupNorm(num_channels=512, num_groups=32),
+            GELU(),
+        ])
+    
+    def compute_lengths(self, waveform_lengths: Tensor) -> Tensor:
+        """Accurately compute output lengths after all convolutions."""
+        lengths = waveform_lengths
+        for module in self.filters:
+            if isinstance(module, Conv1d):
+                # Conv1d with padding=0, dilation=1:
+                # output = floor((input - kernel_size) / stride) + 1
+                lengths = (lengths - module.kernel_size[0]) // module.stride[0] + 1
+        return lengths
+    
+    def forward(self, x: Tensor) -> Tensor:
+        for filter in self.filters:
+            x = filter(x)
+        
+        return x
+
+
+class ASRModel(Module):
+    def __init__(self, vocab_size: int, input_dim: int = 256, num_heads: int = 8, ffn_dim: int = 2048, num_layers: int = 6, dropout: float = 0.1) -> None:
+        super().__init__()
+
+        self.feature_extractor = WaveformFilter()
+        self.proj = Linear(in_features=512, out_features=input_dim, bias=False)
 
         self.encoder = Conformer(input_dim=input_dim, num_heads=num_heads, ffn_dim=ffn_dim, num_layers=num_layers, depthwise_conv_kernel_size=31, dropout=dropout)
 
         self.ctc_head = Linear(in_features=input_dim, out_features=vocab_size, bias=False)
 
-    def forward(self, mel_specs: Tensor, mel_lengths: Tensor) -> tuple[Tensor, Tensor]:
-        # mel_specs: [B, n_mels, time]
-        x: Tensor = mel_specs.unsqueeze(1)  # [B, 1, n_mels, time]
-
-        x = self.relu(self.conv1(x))  # [batch, 16, n_mels/2, time/2]
-        x = self.relu(self.conv2(x))  # [batch, 32, n_mels/4, time/4]
-        x = self.relu(self.conv3(x))  # [batch, 32, n_mels/8, time/4]
-
-        # [B, channels, freq, time] → [B, time, channels*freq]
-        batch, channels, freq, time = x.shape
-        x = x.permute(0, 3, 1, 2).reshape(batch, time, channels * freq)
+    def forward(self, waveforms: Tensor, waveform_lengths: Tensor) -> tuple[Tensor, Tensor]:
+        assert len(waveform_lengths.shape) == 1, "The waveform_lengths tensor must be shape of [B] tensor."
+        assert len(waveforms.shape) == 2, "The waveform tensor must be [B, time] tensor"
+        # waveforms: [B, time]
+        x: Tensor = waveforms.unsqueeze(1)  # [B, 1, time]
+        #x: [B, 1, time]
+        x: Tensor = self.feature_extractor(x)
+        #x: [B, 512, time]
+        x = x.permute(0, 2, 1)
+        #x: [B, time, 512]
         x = self.proj(x)
+        #x: [B, time, 256]
         # lengths = torch.tensor([time] * batch, dtype=torch.long, device=x.device)
-        lengths = ((mel_lengths + 1) // 2 + 1) // 2  # 两层 stride=2
+        lengths = self.feature_extractor.compute_lengths(waveform_lengths)
 
         x, lengths = self.encoder(x, lengths)
 

src/tokenizer.py

@@ -3,7 +3,6 @@ from pathlib import Path
 import re
 import torch
 from torch import Tensor
-
 from handle.text_handle import process_text
 from handle.text_normalizer import UYGHUR_LETTERS
 
@@ -63,8 +62,6 @@ class ASRTokenizer:
                 token_id = self.vocab_to_id.get(token)
                 if token_id is not None:
                     result.append(token_id)
-                elif token in UYGHUR_LETTERS:
-                    result.append(self.vocab_to_id.get(token, self.vocab_to_id['<UNK>']))
                 else:
                     sub_pieces = self._split_long_syllable(token)
                     for piece in sub_pieces:

src/train.py

@@ -1,5 +1,7 @@
+import math
+
 import torch
-from torch import Tensor, device, no_grad, cuda
+from torch import Tensor, device, inference_mode, cuda
 from torch.optim import AdamW, Optimizer
 from torch.optim.lr_scheduler import OneCycleLR
 from torch.nn import CTCLoss, utils
@@ -17,23 +19,23 @@ from model import ASRModel
 # ============ 全局配置 ============
 CONFIG = {
     # 数据配置
-    'batch_size': 96,
+    'batch_size': 32,
     
     # 训练配置
     'num_epochs': 50,
-    'learning_rate': 1e-4,
+    'learning_rate': 2e-5,
     'weight_decay': 1e-4,
     'grad_clip_norm': 1.0,
     
     # 模型配置
-    'input_dim': 640,
+    'input_dim': 256,
     'num_heads': 8,
     'ffn_dim': 2048,
     'num_layers': 8,
     'dropout': 0.1,
     
     # 保存和评估
-    'early_stopping_patience': 12,
+    'early_stopping_patience': 10,
 }
 
 
@@ -91,17 +93,17 @@ def train_one_epoch(model: ASRModel, dataloader: DataLoader, criterion: CTCLoss,
     progress_bar = tqdm(dataloader, desc=f"Epoch {epoch}")
     for batch_index, batch in enumerate(progress_bar):
         batch: Batch
-        mel_specs = batch['mel_specs'].to(device)
+        waveforms = batch['waveforms'].to(device)
         targets = batch['targets'].to(device)
-        mel_lengths = batch['mel_lengths'].to(device)
+        waveform_lengths = batch['waveform_lengths'].to(device)
         target_lengths = batch['target_lengths'].to(device)
 
         optimizer.zero_grad()
 
         with torch.autocast(device_type='cuda', dtype=torch.bfloat16):
-            log_probs, lengths = model(mel_specs=mel_specs, mel_lengths=mel_lengths)
+            log_probs, lengths = model(waveforms=waveforms, waveform_lengths=waveform_lengths)
             log_probs: Tensor
-            log_probs_ctc = log_probs.permute(1, 0, 2)
+            log_probs_ctc = log_probs.permute(1, 0, 2)  # [T, B, vocab_size]
             loss: Tensor = criterion(log_probs=log_probs_ctc, targets=targets, input_lengths=lengths, target_lengths=target_lengths)
 
         scaler.scale(loss).backward()
@@ -122,7 +124,7 @@ def train_one_epoch(model: ASRModel, dataloader: DataLoader, criterion: CTCLoss,
     train_avg_loss = total_train_loss / num_batches
     return train_avg_loss, global_step
 
-def validate(model: ASRModel, dataloader: DataLoader, criterion: CTCLoss, device: device, tokenizer: ASRTokenizer, writer: SummaryWriter, global_step: int) -> tuple[float, float, float]:
+def validate(model: ASRModel, dataloader: DataLoader, criterion: CTCLoss, device: device, tokenizer: ASRTokenizer, writer: SummaryWriter, epoch: int) -> tuple[float, float, float]:
     model.eval()
     total_loss = 0
     total_cer = 0
@@ -131,17 +133,17 @@ def validate(model: ASRModel, dataloader: DataLoader, criterion: CTCLoss, device
     num_batches = 0
     examples = []
 
-    with no_grad():
+    with inference_mode():
         progress_bar = tqdm(dataloader, desc="Validate", leave=False)
         for batch in progress_bar:
             batch: Batch
-            mel_specs = batch['mel_specs'].to(device)
+            waveforms = batch['waveforms'].to(device)
             targets = batch['targets'].to(device)
-            mel_lengths = batch['mel_lengths'].to(device)
+            waveform_lengths = batch['waveform_lengths'].to(device)
             target_lengths = batch['target_lengths'].to(device)
 
             with torch.autocast(device_type='cuda', dtype=torch.bfloat16):
-                log_probs, lengths = model(mel_specs=mel_specs, mel_lengths=mel_lengths)
+                log_probs, lengths = model(waveforms=waveforms, waveform_lengths=waveform_lengths)
                 log_probs: Tensor
                 log_probs_ctc = log_probs.permute(1, 0, 2)
                 loss: Tensor = criterion(log_probs=log_probs_ctc, targets=targets, input_lengths=lengths, target_lengths=target_lengths)
@@ -149,6 +151,7 @@ def validate(model: ASRModel, dataloader: DataLoader, criterion: CTCLoss, device
             total_loss += loss.item()
 
             for i in range(log_probs.shape[0]):
+                # 告诉长度：log_probs[i, :lengths[i]
                 pred_text = tokenizer.ctc_greedy_decode(log_probs=log_probs[i])
                 true_text = batch['target_texts'][i]
                 cer = calculate_cer(pred=pred_text, target=true_text)
@@ -166,17 +169,13 @@ def validate(model: ASRModel, dataloader: DataLoader, criterion: CTCLoss, device
     avg_cer = total_cer / num_samples
     avg_wer = total_wer / num_samples
 
-    writer.add_scalar('Val/Loss', avg_loss, global_step)
-    writer.add_scalar('Val/CER', avg_cer, global_step)
-    writer.add_scalar('Val/WER', avg_wer, global_step)
-
     for index, (true_text, pred_text, cer, wer) in enumerate(examples):
-        writer.add_text(f'Val/Example_{index}', f'True: {true_text}\nPred: {pred_text}\nCER: {cer:.4f} | WER: {wer:.4f}', global_step)
+        writer.add_text(f'Val/Example_{index}', f'True: {true_text}\nPred: {pred_text}\nCER: {cer:.4f} | WER: {wer:.4f}', epoch)
     
     model.train()
     return avg_loss, avg_cer, avg_wer
 
-def save_checkpoint(model: ASRModel, optimizer: Optimizer, scheduler: OneCycleLR, global_step: int, epoch: int, train_loss: float, val_loss: float, cer: float, wer: float, save_path: Path):
+def save_checkpoint(model: ASRModel, optimizer: Optimizer, scheduler: OneCycleLR, global_step: int, epoch: int, train_loss: float, val_loss: float, cer: float, wer: float, current_prob: float, save_path: Path):
     checkpoint = {
         'model_state_dict': model.state_dict(),
         'optimizer_state_dict': optimizer.state_dict(),
@@ -187,43 +186,56 @@ def save_checkpoint(model: ASRModel, optimizer: Optimizer, scheduler: OneCycleLR
         'epoch': epoch,
         'cer': cer,
         'wer': wer,
+        'current_prob': current_prob,
     }
     torch.save(checkpoint, save_path)
 
 def find_latest_checkpoint(checkpoint_dir: Path) -> Path | None:
-    checkpoints = sorted(checkpoint_dir.glob('checkpoint_epoch_*.pt'), key=lambda p: int(p.stem.split('_')[-1]))
+    # checkpoints = sorted(checkpoint_dir.glob('checkpoint_epoch_*.pt'), key=lambda p: int(p.stem.split('_')[-1]))
+    checkpoints = [checkpoint_dir.joinpath('retrain.pt')]
     return checkpoints[-1] if checkpoints else None
 
 def load_checkpoint(file_path: Path, model: ASRModel, optimizer: AdamW, scheduler: OneCycleLR):
     checkpoint = torch.load(file_path, weights_only=False)
     model.load_state_dict(checkpoint['model_state_dict'])
-    optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
-    scheduler.load_state_dict(checkpoint['scheduler_state_dict'])
+    # optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
+    # for param_group in optimizer.param_groups:
+    #     param_group['lr'] = 5e-5 
+    # scheduler.load_state_dict(checkpoint['scheduler_state_dict'])
     
-    epoch = checkpoint['epoch']
-    global_step = checkpoint['global_step']
-    best_cer = checkpoint['cer']
-    best_wer = checkpoint['wer']
-    return epoch, global_step, best_cer, best_wer
+    # epoch = checkpoint['epoch']
+    # global_step = checkpoint['global_step']
+    # best_cer = checkpoint['cer']
+    # best_wer = checkpoint['wer']
+    # current_prob = checkpoint['current_prob']
+    # return epoch, global_step, best_cer, best_wer, current_prob
 
 def main():
     workspace_dir = Path(__file__).parent.parent
     device = torch.device('cuda:0')
     tokenizer = ASRTokenizer(workspace_dir / 'config/asr_vocab.json')
+    final_prob = 0.5
+    warmup_epochs = 6
+    current_prob = 0.0
 
     # ============ 创建数据加载器 ============
     train_loader = create_dataloader(
-        tsv_path=workspace_dir / '.data/ug/train.tsv',
+        tsv_path=workspace_dir / '.data/ug/train_new.tsv',
         audio_dir=workspace_dir / '.data/ug/clips',
+        noise_dir='/mnt/dataset/dataset/audio/noise',
+        corridor_noise_dir= workspace_dir / 'data/corridor',
         tokenizer=tokenizer,
         batch_size=CONFIG['batch_size'],
         shuffle=True,
-        augment=True
+        augment=True,
+        augment_prob=current_prob
     )
     
     val_loader = create_dataloader(
-        tsv_path=workspace_dir / '.data/ug/dev.tsv',
+        tsv_path=workspace_dir / '.data/ug/val_new.tsv',
         audio_dir=workspace_dir / '.data/ug/clips',
+        noise_dir='/mnt/dataset/dataset/audio/noise',
+        corridor_noise_dir= workspace_dir / 'data/corridor',
         tokenizer=tokenizer,
         batch_size=CONFIG['batch_size'],
         shuffle=False,
@@ -245,19 +257,36 @@ def main():
     criterion = CTCLoss(blank=tokenizer.get_special_token_id('<BLANK>'), zero_infinity=True)
     optimizer = AdamW(model.parameters(), lr=CONFIG['learning_rate'], weight_decay=CONFIG['weight_decay'], foreach=True)
 
+    checkpoint_dir = workspace_dir / '.checkpoints'
+    checkpoint_dir.mkdir(exist_ok=True)
+
+    best_cer = float('inf')
+    best_wer = float('inf')
+    patience_counter = 0
+    global_step = 0
+    start_epoch = 0
+
+    latest = find_latest_checkpoint(checkpoint_dir)
+    
     # 使用 OneCycleLR：自动处理 warmup 和衰减
     scheduler = OneCycleLR(
         optimizer,
         max_lr=CONFIG['learning_rate'],
         epochs=CONFIG['num_epochs'],
         steps_per_epoch=len(train_loader),
-        pct_start=0.1,  # 前 10% 步数用于 warmup
+        pct_start=0.1,
         anneal_strategy='cos',
-        div_factor=25.0,  # 初始 lr = max_lr / 25
-        final_div_factor=1e4,  # 最终 lr = max_lr / 10000
+        div_factor=10.0,
+        final_div_factor=1e4,
     )
     scaler = GradScaler()
-    
+    load_checkpoint(latest, model, optimizer, scheduler)
+    # if latest:
+    #     start_epoch, global_step, best_cer, best_wer, current_prob = load_checkpoint(latest, model, optimizer, scheduler)
+    #     print(f"✅ 恢复训练: 从 epoch={start_epoch} 开始, global_step={global_step}")
+    # else:
+    #     start_epoch = 0
+    #     print("🆕 从头开始训练\n")
     # ============ TensorBoard ============
     log_dir = workspace_dir / 'runs' / datetime.now().strftime('%Y%m%d_%H%M%S')
     writer = SummaryWriter(log_dir)
@@ -266,26 +295,12 @@ def main():
     writer.add_text('Config', config_text, 0)
     print(f"📊 TensorBoard 日志: {log_dir}")
 
-    checkpoint_dir = workspace_dir / '.checkpoints'
-    checkpoint_dir.mkdir(exist_ok=True)
-
     # ============ 训练循环 ============
-    best_cer = float('inf')
-    best_wer = float('inf')
-    patience_counter = 0
-    global_step = 0
-    start_epoch = 0
-
-    latest = find_latest_checkpoint(checkpoint_dir)
-    if latest:
-        start_epoch, global_step, best_cer, best_wer = load_checkpoint(latest, model, optimizer, scheduler)
-        start_epoch += 1  # 从下一个 epoch 开始
-        print(f"✅ 恢复训练: 从 epoch={start_epoch} 开始, global_step={global_step}")
-    else:
-        start_epoch = 0
-        print("🆕 从头开始训练\n")
-
     for epoch in range(start_epoch, CONFIG['num_epochs']):
+        epoch = epoch + 1
+        current_prob = final_prob * min(1.0, epoch / warmup_epochs)
+        train_loader.dataset.augment_prob = current_prob
+        print(f"📈 Epoch {epoch} | Augment Prob: {train_loader.dataset.augment_prob:.2f}")
         train_loss, global_step = train_one_epoch(
             model=model,
             dataloader=train_loader, 
@@ -299,25 +314,25 @@ def main():
             scaler=scaler,
         )
 
-        val_loss, val_cer, val_wer = validate(model=model, dataloader=val_loader, criterion=criterion, device=device, tokenizer=tokenizer, writer=writer, global_step=global_step)
+        val_loss, val_cer, val_wer = validate(model=model, dataloader=val_loader, criterion=criterion, device=device, tokenizer=tokenizer, writer=writer, epoch=epoch)
         print(f"\n📊 Step {global_step} | Val Loss: {val_loss:.4f} | Val CER: {val_cer:.4f} | Val WER: {val_wer:.4f}")
         
         # 保存常规 checkpoint
         checkpoint_path = checkpoint_dir / f'checkpoint_epoch_{epoch}.pt'
-        save_checkpoint(model=model, optimizer=optimizer, scheduler=scheduler, epoch=epoch, global_step=global_step, train_loss=train_loss, val_loss=val_loss, cer=val_cer, wer=val_wer, save_path=checkpoint_path)
+        save_checkpoint(model=model, optimizer=optimizer, scheduler=scheduler, epoch=epoch, global_step=global_step, train_loss=train_loss, val_loss=val_loss, cer=val_cer, wer=val_wer, current_prob=current_prob, save_path=checkpoint_path)
         
         # 分别保存最佳 CER 和 WER 模型
         improved = False
         if val_cer < best_cer:
             best_cer = val_cer
             best_cer_path = checkpoint_dir / 'best_cer_model.pt'
-            save_checkpoint(model=model, optimizer=optimizer, scheduler=scheduler, epoch=epoch, global_step=global_step, train_loss=train_loss, val_loss=val_loss, cer=val_cer, wer=val_wer, save_path=best_cer_path)
+            save_checkpoint(model=model, optimizer=optimizer, scheduler=scheduler, epoch=epoch, global_step=global_step, train_loss=train_loss, val_loss=val_loss, cer=val_cer, wer=val_wer, current_prob=current_prob, save_path=best_cer_path)
             improved = True
         
         if val_wer < best_wer:
             best_wer = val_wer
             best_wer_path = checkpoint_dir / 'best_wer_model.pt'
-            save_checkpoint(model=model, optimizer=optimizer, scheduler=scheduler, epoch=epoch, global_step=global_step, train_loss=train_loss, val_loss=val_loss, cer=val_cer, wer=val_wer, save_path=best_wer_path)
+            save_checkpoint(model=model, optimizer=optimizer, scheduler=scheduler, epoch=epoch, global_step=global_step, train_loss=train_loss, val_loss=val_loss, cer=val_cer, wer=val_wer, current_prob=current_prob, save_path=best_wer_path)
             improved = True
         
         # Early Stopping 逻辑
@@ -334,8 +349,10 @@ def main():
 
         cuda.empty_cache()
 
-        writer.add_scalar('Val/EpochLoss', val_loss, epoch)
         writer.add_scalar('Train/EpochLoss', train_loss, epoch)
+        writer.add_scalar('Val/EpochLoss', val_loss, epoch)
+        writer.add_scalar('Val/CER', val_cer, epoch)
+        writer.add_scalar('Val/WER', val_wer, epoch)
         print(f"✅ Epoch {epoch} 完成 | Train Avg Loss: {train_loss:.4f} | Val Avg Loss: {val_loss:.4f} | Best CER: {best_cer:.4f} | Best WER: {best_wer:.4f}\n")
         
         # Early Stopping 检查

src/validate.py

@@ -0,0 +1,132 @@
+
+
+from email.headerregistry import DateHeader
+from pathlib import Path
+
+from torch import Tensor, inference_mode
+import torch
+from torch.nn import CTCLoss
+from tqdm import tqdm
+
+from dataset import Batch, create_dataloader
+from model import ASRModel
+from tokenizer import ASRTokenizer
+from train import calculate_cer, calculate_wer
+
+def validate(model: ASRModel, dataloader: DateHeader, criterion: CTCLoss, device: torch.device, tokenizer: ASRTokenizer) -> tuple[float, float, float]:
+    model.eval()
+    total_loss = 0
+    total_cer = 0
+    total_wer = 0
+    num_samples = 0
+    num_batches = 0
+    examples = []
+
+    with inference_mode():
+        progress_bar = tqdm(dataloader, desc="Validate", leave=False)
+        for batch in progress_bar:
+            batch: Batch
+            waveforms = batch['waveforms'].to(device)
+            targets = batch['targets'].to(device)
+            waveform_lengths = batch['waveform_lengths'].to(device)
+            target_lengths = batch['target_lengths'].to(device)
+
+            with torch.autocast(device_type='cuda', dtype=torch.float16):
+                log_probs, lengths = model(waveforms=waveforms, waveform_lengths=waveform_lengths)
+                log_probs: Tensor
+                log_probs_ctc = log_probs.permute(1, 0, 2)
+                loss: Tensor = criterion(log_probs=log_probs_ctc, targets=targets, input_lengths=lengths, target_lengths=target_lengths)
+            
+            total_loss += loss.item()
+            diff_count = 0
+            printed_diff = 0
+
+            for i in range(log_probs.shape[0]):
+                pred_full = tokenizer.ctc_greedy_decode(log_probs=log_probs[i])
+                pred_sliced = tokenizer.ctc_greedy_decode(log_probs=log_probs[i, :lengths[i]])
+
+                if pred_full != pred_sliced:
+                    diff_count += 1
+
+                    if printed_diff < 5:
+                        print("\nDECODE DIFF FOUND")
+                        print("audio:", batch["audio_paths"][i])
+                        print("waveform_length:", waveform_lengths[i].item())
+                        print("model_valid_length:", lengths[i].item())
+                        print("model_full_length:", log_probs.shape[1])
+                        print("target:", batch["target_texts"][i])
+                        print("full:", pred_full)
+                        print("sliced:", pred_sliced)
+                        printed_diff += 1
+
+                pred_text = pred_sliced
+                true_text = batch['target_texts'][i]
+                cer = calculate_cer(pred=pred_text, target=true_text)
+                wer = calculate_wer(pred=pred_text, target=true_text)
+                total_cer += cer
+                total_wer += wer
+                num_samples += 1
+
+                if len(examples) < 3:
+                    examples.append((true_text, pred_text, cer, wer))
+
+            num_batches += 1
+
+    avg_loss = total_loss / num_batches
+    avg_cer = total_cer / num_samples
+    avg_wer = total_wer / num_samples
+
+    return avg_loss, avg_cer, avg_wer
+
+
+CONFIG = {
+    # 数据配置
+    'batch_size': 32,
+    
+    # 训练配置
+    'num_epochs': 50,
+    'learning_rate': 2e-5,
+    'weight_decay': 1e-4,
+    'grad_clip_norm': 1.0,
+    
+    # 模型配置
+    'input_dim': 256,
+    'num_heads': 8,
+    'ffn_dim': 2048,
+    'num_layers': 8,
+    'dropout': 0.1,
+    
+    # 保存和评估
+    'early_stopping_patience': 10,
+}
+device = torch.device('cuda:1')
+workspace_dir = Path(__file__).parent.parent
+tokenizer = ASRTokenizer(workspace_dir / 'config/asr_vocab.json')
+model = ASRModel(
+    vocab_size=tokenizer.vocab_size(),
+    input_dim=CONFIG['input_dim'],
+    num_heads=CONFIG['num_heads'],
+    ffn_dim=CONFIG['ffn_dim'],
+    num_layers=CONFIG['num_layers'],
+    dropout=CONFIG['dropout'],
+).to(device)
+
+checkpoint = workspace_dir / ".checkpoints/checkpoint_epoch_12.pt"
+model.load_state_dict(torch.load(checkpoint, map_location=device)['model_state_dict'])
+print(f"🤖 模型参数量: {model.get_num_params() / 1e6:.2f}M")
+
+
+val_loader = create_dataloader(
+    tsv_path=workspace_dir / '.data/ug/val_new.tsv',
+    audio_dir=workspace_dir / '.data/ug/clips',
+    noise_dir='/mnt/dataset/dataset/audio/noise',
+    corridor_noise_dir= workspace_dir / 'data/corridor',
+    tokenizer=tokenizer,
+    batch_size=10,
+    shuffle=False,
+    augment=False
+)
+
+criterion = CTCLoss(blank=tokenizer.get_special_token_id('<BLANK>'), zero_infinity=True)
+val_loss, val_cer, val_wer = validate(model=model, dataloader=val_loader, criterion=criterion, device=device, tokenizer=tokenizer)
+print(f"\n📊 Val Loss: {val_loss:.4f} | Clean Val CER: {val_cer:.4f} | Clean Val WER: {val_wer:.4f}")

uv.lock

@@ -6,10 +6,10 @@ resolution-markers = [
     "python_full_version >= '3.14' and sys_platform == 'emscripten'",
     "python_full_version >= '3.14' and sys_platform != 'emscripten' and sys_platform != 'win32'",
     "python_full_version == '3.13.*' and sys_platform == 'win32'",
-    "python_full_version == '3.12.*' and sys_platform == 'win32'",
     "python_full_version == '3.13.*' and sys_platform == 'emscripten'",
-    "python_full_version == '3.12.*' and sys_platform == 'emscripten'",
     "python_full_version == '3.13.*' and sys_platform != 'emscripten' and sys_platform != 'win32'",
+    "python_full_version == '3.12.*' and sys_platform == 'win32'",
+    "python_full_version == '3.12.*' and sys_platform == 'emscripten'",
     "python_full_version == '3.12.*' and sys_platform != 'emscripten' and sys_platform != 'win32'",
     "python_full_version < '3.12' and sys_platform == 'win32'",
     "python_full_version < '3.12' and sys_platform == 'emscripten'",
@@ -34,6 +34,55 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d2/39/e7eaf1799466a4aef85b6a4fe7bd175ad2b1c6345066aa33f1f58d4b18d0/asttokens-3.0.1-py3-none-any.whl", hash = "sha256:15a3ebc0f43c2d0a50eeafea25e19046c68398e487b9f1f5b517f7c0f40f976a", size = 27047, upload-time = "2025-11-15T16:43:16.109Z" },
 ]
 
+[[package]]
+name = "audio-model"
+version = "0.1.0"
+source = { virtual = "." }
+dependencies = [
+    { name = "ipython" },
+    { name = "librosa" },
+    { name = "matplotlib" },
+    { name = "mutagen" },
+    { name = "numpy" },
+    { name = "pandas" },
+    { name = "pillow" },
+    { name = "pydub" },
+    { name = "pyrubberband" },
+    { name = "setuptools" },
+    { name = "silero-vad" },
+    { name = "tensorboard" },
+    { name = "tensorboardx" },
+    { name = "torch" },
+    { name = "torch-audiomentations" },
+    { name = "torchaudio" },
+    { name = "torchcodec" },
+    { name = "tqdm" },
+    { name = "webrtcvad" },
+]
+
+[package.metadata]
+requires-dist = [
+    { name = "ipython", specifier = ">=9.10.1" },
+    { name = "librosa", specifier = ">=0.11.0" },
+    { name = "matplotlib", specifier = ">=3.10.8" },
+    { name = "mutagen", specifier = ">=1.47.0" },
+    { name = "numpy", specifier = ">=2.4.4" },
+    { name = "pandas", specifier = ">=3.0.2" },
+    { name = "pillow", specifier = ">=12.2.0" },
+    { name = "pydub", specifier = ">=0.25.1" },
+    { name = "pyrubberband", specifier = ">=0.4.0" },
+    { name = "setuptools", specifier = "<82" },
+    { name = "silero-vad", specifier = ">=6.2.1" },
+    { name = "tensorboard", specifier = ">=2.20.0" },
+    { name = "tensorboardx", specifier = ">=2.6.5" },
+    { name = "torch", specifier = "==2.8.0" },
+    { name = "torch-audiomentations", specifier = ">=0.12.0" },
+    { name = "torchaudio", specifier = "==2.8.0" },
+    { name = "torchcodec", specifier = "==0.7.0" },
+    { name = "tqdm", specifier = ">=4.67.3" },
+    { name = "webrtcvad", specifier = ">=2.0.10" },
+]
+
 [[package]]
 name = "audioop-lts"
 version = "0.2.2"
@@ -373,11 +422,11 @@ wheels = [
 
 [[package]]
 name = "decorator"
-version = "5.2.1"
+version = "5.3.1"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/43/fa/6d96a0978d19e17b68d634497769987b16c8f4cd0a7a05048bec693caa6b/decorator-5.2.1.tar.gz", hash = "sha256:65f266143752f734b0a7cc83c46f4618af75b8c5911b00ccb61d0ac9b6da0360", size = 56711, upload-time = "2025-02-24T04:41:34.073Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/60/8b/32f9823da46cde7df2087faa08cd98d01b908f8dcab982cdba9c84e85355/decorator-5.3.1.tar.gz", hash = "sha256:4cbcdd55a6efadb9dbea26b858f4fb3264567b52d69ca0d25b721b553f60ea82", size = 58084, upload-time = "2026-05-18T06:03:28.057Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/4e/8c/f3147f5c4b73e7550fe5f9352eaa956ae838d5c51eb58e7a25b9f3e2643b/decorator-5.2.1-py3-none-any.whl", hash = "sha256:d316bb415a2d9e2d2b3abcc4084c6502fc09240e292cd76a76afc106a1c8e04a", size = 9190, upload-time = "2025-02-24T04:41:32.565Z" },
+    { url = "https://files.pythonhosted.org/packages/05/7f/798705f5296a58ca505d600456748d1be48078eac8a7050d8a98bc9edb89/decorator-5.3.1-py3-none-any.whl", hash = "sha256:f47fe6fdbd2edd623ecfe36875d37aba411624e2670dd395dddae1358689bb3c", size = 10365, upload-time = "2026-05-18T06:03:26.517Z" },
 ]
 
 [[package]]
@@ -400,60 +449,60 @@ wheels = [
 
 [[package]]
 name = "fonttools"
-version = "4.62.1"
+version = "4.63.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/9a/08/7012b00a9a5874311b639c3920270c36ee0c445b69d9989a85e5c92ebcb0/fonttools-4.62.1.tar.gz", hash = "sha256:e54c75fd6041f1122476776880f7c3c3295ffa31962dc6ebe2543c00dca58b5d", size = 3580737, upload-time = "2026-03-13T13:54:25.52Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/84/69/c97f2c18e0db87d2c7b15da1974dace76ae938f1cfa22e2727a648b7ed43/fonttools-4.63.0.tar.gz", hash = "sha256:caeb583deeb5168e694b65cda8b4ee62abedfa66cf88488734466f2366b9c4e0", size = 3597189, upload-time = "2026-05-14T12:04:30.958Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/88/39/23ff32561ec8d45a4d48578b4d241369d9270dc50926c017570e60893701/fonttools-4.62.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:40975849bac44fb0b9253d77420c6d8b523ac4dcdcefeff6e4d706838a5b80f7", size = 2871039, upload-time = "2026-03-13T13:52:33.127Z" },
-    { url = "https://files.pythonhosted.org/packages/24/7f/66d3f8a9338a9b67fe6e1739f47e1cd5cee78bd3bc1206ef9b0b982289a5/fonttools-4.62.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:9dde91633f77fa576879a0c76b1d89de373cae751a98ddf0109d54e173b40f14", size = 2416346, upload-time = "2026-03-13T13:52:35.676Z" },
-    { url = "https://files.pythonhosted.org/packages/aa/53/5276ceba7bff95da7793a07c5284e1da901cf00341ce5e2f3273056c0cca/fonttools-4.62.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6acb4109f8bee00fec985c8c7afb02299e35e9c94b57287f3ea542f28bd0b0a7", size = 5100897, upload-time = "2026-03-13T13:52:38.102Z" },
-    { url = "https://files.pythonhosted.org/packages/cc/a1/40a5c4d8e28b0851d53a8eeeb46fbd73c325a2a9a165f290a5ed90e6c597/fonttools-4.62.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:1c5c25671ce8805e0d080e2ffdeca7f1e86778c5cbfbeae86d7f866d8830517b", size = 5071078, upload-time = "2026-03-13T13:52:41.305Z" },
-    { url = "https://files.pythonhosted.org/packages/e3/be/d378fca4c65ea1956fee6d90ace6e861776809cbbc5af22388a090c3c092/fonttools-4.62.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:a5d8825e1140f04e6c99bb7d37a9e31c172f3bc208afbe02175339e699c710e1", size = 5076908, upload-time = "2026-03-13T13:52:44.122Z" },
-    { url = "https://files.pythonhosted.org/packages/f8/d9/ae6a1d0693a4185a84605679c8a1f719a55df87b9c6e8e817bfdd9ef5936/fonttools-4.62.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:268abb1cb221e66c014acc234e872b7870d8b5d4657a83a8f4205094c32d2416", size = 5202275, upload-time = "2026-03-13T13:52:46.591Z" },
-    { url = "https://files.pythonhosted.org/packages/54/6c/af95d9c4efb15cabff22642b608342f2bd67137eea6107202d91b5b03184/fonttools-4.62.1-cp311-cp311-win32.whl", hash = "sha256:942b03094d7edbb99bdf1ae7e9090898cad7bf9030b3d21f33d7072dbcb51a53", size = 2293075, upload-time = "2026-03-13T13:52:48.711Z" },
-    { url = "https://files.pythonhosted.org/packages/d3/97/bf54c5b3f2be34e1f143e6db838dfdc54f2ffa3e68c738934c82f3b2a08d/fonttools-4.62.1-cp311-cp311-win_amd64.whl", hash = "sha256:e8514f4924375f77084e81467e63238b095abda5107620f49421c368a6017ed2", size = 2344593, upload-time = "2026-03-13T13:52:50.725Z" },
-    { url = "https://files.pythonhosted.org/packages/47/d4/dbacced3953544b9a93088cc10ef2b596d348c983d5c67a404fa41ec51ba/fonttools-4.62.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:90365821debbd7db678809c7491ca4acd1e0779b9624cdc6ddaf1f31992bf974", size = 2870219, upload-time = "2026-03-13T13:52:53.664Z" },
-    { url = "https://files.pythonhosted.org/packages/66/9e/a769c8e99b81e5a87ab7e5e7236684de4e96246aae17274e5347d11ebd78/fonttools-4.62.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:12859ff0b47dd20f110804c3e0d0970f7b832f561630cd879969011541a464a9", size = 2414891, upload-time = "2026-03-13T13:52:56.493Z" },
-    { url = "https://files.pythonhosted.org/packages/69/64/f19a9e3911968c37e1e620e14dfc5778299e1474f72f4e57c5ec771d9489/fonttools-4.62.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9c125ffa00c3d9003cdaaf7f2c79e6e535628093e14b5de1dccb08859b680936", size = 5033197, upload-time = "2026-03-13T13:52:59.179Z" },
-    { url = "https://files.pythonhosted.org/packages/9b/8a/99c8b3c3888c5c474c08dbfd7c8899786de9604b727fcefb055b42c84bba/fonttools-4.62.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:149f7d84afca659d1a97e39a4778794a2f83bf344c5ee5134e09995086cc2392", size = 4988768, upload-time = "2026-03-13T13:53:02.761Z" },
-    { url = "https://files.pythonhosted.org/packages/d1/c6/0f904540d3e6ab463c1243a0d803504826a11604c72dd58c2949796a1762/fonttools-4.62.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:0aa72c43a601cfa9273bb1ae0518f1acadc01ee181a6fc60cd758d7fdadffc04", size = 4971512, upload-time = "2026-03-13T13:53:05.678Z" },
-    { url = "https://files.pythonhosted.org/packages/29/0b/5cbef6588dc9bd6b5c9ad6a4d5a8ca384d0cea089da31711bbeb4f9654a6/fonttools-4.62.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:19177c8d96c7c36359266e571c5173bcee9157b59cfc8cb0153c5673dc5a3a7d", size = 5122723, upload-time = "2026-03-13T13:53:08.662Z" },
-    { url = "https://files.pythonhosted.org/packages/4a/47/b3a5342d381595ef439adec67848bed561ab7fdb1019fa522e82101b7d9c/fonttools-4.62.1-cp312-cp312-win32.whl", hash = "sha256:a24decd24d60744ee8b4679d38e88b8303d86772053afc29b19d23bb8207803c", size = 2281278, upload-time = "2026-03-13T13:53:10.998Z" },
-    { url = "https://files.pythonhosted.org/packages/28/b1/0c2ab56a16f409c6c8a68816e6af707827ad5d629634691ff60a52879792/fonttools-4.62.1-cp312-cp312-win_amd64.whl", hash = "sha256:9e7863e10b3de72376280b515d35b14f5eeed639d1aa7824f4cf06779ec65e42", size = 2331414, upload-time = "2026-03-13T13:53:13.992Z" },
-    { url = "https://files.pythonhosted.org/packages/3b/56/6f389de21c49555553d6a5aeed5ac9767631497ac836c4f076273d15bd72/fonttools-4.62.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:c22b1014017111c401469e3acc5433e6acf6ebcc6aa9efb538a533c800971c79", size = 2865155, upload-time = "2026-03-13T13:53:16.132Z" },
-    { url = "https://files.pythonhosted.org/packages/03/c5/0e3966edd5ec668d41dfe418787726752bc07e2f5fd8c8f208615e61fa89/fonttools-4.62.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:68959f5fc58ed4599b44aad161c2837477d7f35f5f79402d97439974faebfebe", size = 2412802, upload-time = "2026-03-13T13:53:18.878Z" },
-    { url = "https://files.pythonhosted.org/packages/52/94/e6ac4b44026de7786fe46e3bfa0c87e51d5d70a841054065d49cd62bb909/fonttools-4.62.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ef46db46c9447103b8f3ff91e8ba009d5fe181b1920a83757a5762551e32bb68", size = 5013926, upload-time = "2026-03-13T13:53:21.379Z" },
-    { url = "https://files.pythonhosted.org/packages/e2/98/8b1e801939839d405f1f122e7d175cebe9aeb4e114f95bfc45e3152af9a7/fonttools-4.62.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:6706d1cb1d5e6251a97ad3c1b9347505c5615c112e66047abbef0f8545fa30d1", size = 4964575, upload-time = "2026-03-13T13:53:23.857Z" },
-    { url = "https://files.pythonhosted.org/packages/46/76/7d051671e938b1881670528fec69cc4044315edd71a229c7fd712eaa5119/fonttools-4.62.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:2e7abd2b1e11736f58c1de27819e1955a53267c21732e78243fa2fa2e5c1e069", size = 4953693, upload-time = "2026-03-13T13:53:26.569Z" },
-    { url = "https://files.pythonhosted.org/packages/1f/ae/b41f8628ec0be3c1b934fc12b84f4576a5c646119db4d3bdd76a217c90b5/fonttools-4.62.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:403d28ce06ebfc547fbcb0cb8b7f7cc2f7a2d3e1a67ba9a34b14632df9e080f9", size = 5094920, upload-time = "2026-03-13T13:53:29.329Z" },
-    { url = "https://files.pythonhosted.org/packages/f2/f6/53a1e9469331a23dcc400970a27a4caa3d9f6edbf5baab0260285238b884/fonttools-4.62.1-cp313-cp313-win32.whl", hash = "sha256:93c316e0f5301b2adbe6a5f658634307c096fd5aae60a5b3412e4f3e1728ab24", size = 2279928, upload-time = "2026-03-13T13:53:32.352Z" },
-    { url = "https://files.pythonhosted.org/packages/38/60/35186529de1db3c01f5ad625bde07c1f576305eab6d86bbda4c58445f721/fonttools-4.62.1-cp313-cp313-win_amd64.whl", hash = "sha256:7aa21ff53e28a9c2157acbc44e5b401149d3c9178107130e82d74ceb500e5056", size = 2330514, upload-time = "2026-03-13T13:53:34.991Z" },
-    { url = "https://files.pythonhosted.org/packages/36/f0/2888cdac391807d68d90dcb16ef858ddc1b5309bfc6966195a459dd326e2/fonttools-4.62.1-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:fa1d16210b6b10a826d71bed68dd9ec24a9e218d5a5e2797f37c573e7ec215ca", size = 2864442, upload-time = "2026-03-13T13:53:37.509Z" },
-    { url = "https://files.pythonhosted.org/packages/4b/b2/e521803081f8dc35990816b82da6360fa668a21b44da4b53fc9e77efcd62/fonttools-4.62.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:aa69d10ed420d8121118e628ad47d86e4caa79ba37f968597b958f6cceab7eca", size = 2410901, upload-time = "2026-03-13T13:53:40.55Z" },
-    { url = "https://files.pythonhosted.org/packages/00/a4/8c3511ff06e53110039358dbbdc1a65d72157a054638387aa2ada300a8b8/fonttools-4.62.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:bd13b7999d59c5eb1c2b442eb2d0c427cb517a0b7a1f5798fc5c9e003f5ff782", size = 4999608, upload-time = "2026-03-13T13:53:42.798Z" },
-    { url = "https://files.pythonhosted.org/packages/28/63/cd0c3b26afe60995a5295f37c246a93d454023726c3261cfbb3559969bb9/fonttools-4.62.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:8d337fdd49a79b0d51c4da87bc38169d21c3abbf0c1aa9367eff5c6656fb6dae", size = 4912726, upload-time = "2026-03-13T13:53:45.405Z" },
-    { url = "https://files.pythonhosted.org/packages/70/b9/ac677cb07c24c685cf34f64e140617d58789d67a3dd524164b63648c6114/fonttools-4.62.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:d241cdc4a67b5431c6d7f115fdf63335222414995e3a1df1a41e1182acd4bcc7", size = 4951422, upload-time = "2026-03-13T13:53:48.326Z" },
-    { url = "https://files.pythonhosted.org/packages/e6/10/11c08419a14b85b7ca9a9faca321accccc8842dd9e0b1c8a72908de05945/fonttools-4.62.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:c05557a78f8fa514da0f869556eeda40887a8abc77c76ee3f74cf241778afd5a", size = 5060979, upload-time = "2026-03-13T13:53:51.366Z" },
-    { url = "https://files.pythonhosted.org/packages/4e/3c/12eea4a4cf054e7ab058ed5ceada43b46809fce2bf319017c4d63ae55bb4/fonttools-4.62.1-cp314-cp314-win32.whl", hash = "sha256:49a445d2f544ce4a69338694cad575ba97b9a75fff02720da0882d1a73f12800", size = 2283733, upload-time = "2026-03-13T13:53:53.606Z" },
-    { url = "https://files.pythonhosted.org/packages/6b/67/74b070029043186b5dd13462c958cb7c7f811be0d2e634309d9a1ffb1505/fonttools-4.62.1-cp314-cp314-win_amd64.whl", hash = "sha256:1eecc128c86c552fb963fe846ca4e011b1be053728f798185a1687502f6d398e", size = 2335663, upload-time = "2026-03-13T13:53:56.23Z" },
-    { url = "https://files.pythonhosted.org/packages/42/c5/4d2ed3ca6e33617fc5624467da353337f06e7f637707478903c785bd8e20/fonttools-4.62.1-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:1596aeaddf7f78e21e68293c011316a25267b3effdaccaf4d59bc9159d681b82", size = 2947288, upload-time = "2026-03-13T13:53:59.397Z" },
-    { url = "https://files.pythonhosted.org/packages/1f/e9/7ab11ddfda48ed0f89b13380e5595ba572619c27077be0b2c447a63ff351/fonttools-4.62.1-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:8f8fca95d3bb3208f59626a4b0ea6e526ee51f5a8ad5d91821c165903e8d9260", size = 2449023, upload-time = "2026-03-13T13:54:01.642Z" },
-    { url = "https://files.pythonhosted.org/packages/b2/10/a800fa090b5e8819942e54e19b55fc7c21fe14a08757c3aa3ca8db358939/fonttools-4.62.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ee91628c08e76f77b533d65feb3fbe6d9dad699f95be51cf0d022db94089cdc4", size = 5137599, upload-time = "2026-03-13T13:54:04.495Z" },
-    { url = "https://files.pythonhosted.org/packages/37/dc/8ccd45033fffd74deb6912fa1ca524643f584b94c87a16036855b498a1ed/fonttools-4.62.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:5f37df1cac61d906e7b836abe356bc2f34c99d4477467755c216b72aa3dc748b", size = 4920933, upload-time = "2026-03-13T13:54:07.557Z" },
-    { url = "https://files.pythonhosted.org/packages/99/eb/e618adefb839598d25ac8136cd577925d6c513dc0d931d93b8af956210f0/fonttools-4.62.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:92bb00a947e666169c99b43753c4305fc95a890a60ef3aeb2a6963e07902cc87", size = 5016232, upload-time = "2026-03-13T13:54:10.611Z" },
-    { url = "https://files.pythonhosted.org/packages/d9/5f/9b5c9bfaa8ec82def8d8168c4f13615990d6ce5996fe52bd49bfb5e05134/fonttools-4.62.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:bdfe592802ef939a0e33106ea4a318eeb17822c7ee168c290273cbd5fabd746c", size = 5042987, upload-time = "2026-03-13T13:54:13.569Z" },
-    { url = "https://files.pythonhosted.org/packages/90/aa/dfbbe24c6a6afc5c203d90cc0343e24bcbb09e76d67c4d6eef8c2558d7ba/fonttools-4.62.1-cp314-cp314t-win32.whl", hash = "sha256:b820fcb92d4655513d8402d5b219f94481c4443d825b4372c75a2072aa4b357a", size = 2348021, upload-time = "2026-03-13T13:54:16.98Z" },
-    { url = "https://files.pythonhosted.org/packages/13/6f/ae9c4e4dd417948407b680855c2c7790efb52add6009aaecff1e3bc50e8e/fonttools-4.62.1-cp314-cp314t-win_amd64.whl", hash = "sha256:59b372b4f0e113d3746b88985f1c796e7bf830dd54b28374cd85c2b8acd7583e", size = 2414147, upload-time = "2026-03-13T13:54:19.416Z" },
-    { url = "https://files.pythonhosted.org/packages/fd/ba/56147c165442cc5ba7e82ecf301c9a68353cede498185869e6e02b4c264f/fonttools-4.62.1-py3-none-any.whl", hash = "sha256:7487782e2113861f4ddcc07c3436450659e3caa5e470b27dc2177cade2d8e7fd", size = 1152647, upload-time = "2026-03-13T13:54:22.735Z" },
+    { url = "https://files.pythonhosted.org/packages/75/2b/a7f1545bdf5da69c4bda0cea2a5781f0ad2a6623e0277267672db43c5fe6/fonttools-4.63.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:2b8ae05d9eacf6081414d759c0a352769ac28ce31280d6bb8e77b03f9e3c449f", size = 2881793, upload-time = "2026-05-14T12:02:56.645Z" },
+    { url = "https://files.pythonhosted.org/packages/49/50/965308c703f085f225db2886813b27e015b8b3438c350b22dd65b52c2a2c/fonttools-4.63.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:79cdc9f567aec74a72918fd060283911406750cbc9fd28c1316023deb6ce31a9", size = 2428130, upload-time = "2026-05-14T12:02:58.891Z" },
+    { url = "https://files.pythonhosted.org/packages/d8/38/6937fbd7f2dc3a6b48725851bc2c15ec949b9af14d9bbcb5fe83cdf9bdf9/fonttools-4.63.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2c14b4fd138c4bafcca294765c547914e1aa431ae1ca94ab99d8db08c958bd3b", size = 5111952, upload-time = "2026-05-14T12:03:01.263Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/43/a81f20050a3115b57d62c8e781446949512eac36690dc384ccea65ff4cc1/fonttools-4.63.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d76ac49f929aecaf82d83250b8347e099d7aecba0f4726c1d9b6df3b8bb5fe18", size = 5082308, upload-time = "2026-05-14T12:03:03.211Z" },
+    { url = "https://files.pythonhosted.org/packages/67/00/cdd9d4944ca6ae280d01e69cc37bde3bf663630b837a6fc6d2cd65d80e0e/fonttools-4.63.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:dcf076a4474fe0d7367e5bbf5b052c7284fa1feca729c04176ce513521afd8a0", size = 5087932, upload-time = "2026-05-14T12:03:05.147Z" },
+    { url = "https://files.pythonhosted.org/packages/f5/f1/0aa0dbea778c75adbef223c42019fd47d22262b905974d62d829545d485f/fonttools-4.63.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:7dd683fef0663e9f0f45cf541d788d24caa3ec9db50796b588e1757d8b3bc007", size = 5213271, upload-time = "2026-05-14T12:03:07.238Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/99/253e4056e1f0e67b9390125a154b73b5eb73ad521bece95c004858fdeec2/fonttools-4.63.0-cp311-cp311-win32.whl", hash = "sha256:afefc1ed0a59785a7fb06ea7e1678e849c193e1e387db783579bc7b3056fcfcb", size = 2304473, upload-time = "2026-05-14T12:03:09.271Z" },
+    { url = "https://files.pythonhosted.org/packages/08/60/defa5e69641db890a63be281f41345f4c33b157824eaf0b9fad3e08b0dcb/fonttools-4.63.0-cp311-cp311-win_amd64.whl", hash = "sha256:063e08bd17bd5a90127a14123de0d6a952dbc847695fd98b63c043d58057f90c", size = 2356389, upload-time = "2026-05-14T12:03:11.53Z" },
+    { url = "https://files.pythonhosted.org/packages/08/ef/b3c6b9b5be2f82416d73fe2ed2e96e2793cd80e7510bd6a17ca79cdd88ec/fonttools-4.63.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:37dd23e621e3b0aef1baa70a303b80aaf38449632cfc8fd2a55fb285bbccfc02", size = 2881131, upload-time = "2026-05-14T12:03:13.386Z" },
+    { url = "https://files.pythonhosted.org/packages/44/a0/c815bea63117fa63e4e1c01f8a1110d2112fa003f838e6467094ec2432ce/fonttools-4.63.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:a9faff9e0c1f76f9fd55899d2ce785832efebab37eb8ae13995853aef178bef0", size = 2426704, upload-time = "2026-05-14T12:03:15.801Z" },
+    { url = "https://files.pythonhosted.org/packages/44/04/0b91d8e916e92ad1fac9e4624760baf0fd5ff2ead614c2f68fb21373f03f/fonttools-4.63.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ef3048ef05dbb552b89817713d9cac912e00d0fde4a3105c00d29e52e10c89af", size = 5044298, upload-time = "2026-05-14T12:03:18.085Z" },
+    { url = "https://files.pythonhosted.org/packages/77/c7/2342da9830e3e9d4870305ca5d2091d2a83284f2953079b7bdd3b5e029d8/fonttools-4.63.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:58dc6bb86a78d782f00f9190ca02c119cf5bbe2807536e361e18d42019f877d8", size = 4999800, upload-time = "2026-05-14T12:03:20.161Z" },
+    { url = "https://files.pythonhosted.org/packages/e6/6d/67fe16c48d7ce050979b33f47e0d28a318f02da030602e944c34f7a16ef3/fonttools-4.63.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:ee08ebfa58f6e1aeff5697ab9582105bb620008c1caafb681e4c557e7483027b", size = 4982666, upload-time = "2026-05-14T12:03:22.87Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/00/3bbab338c07c71fa56269953845e92c951a61457bbbb0f1022551ea266d9/fonttools-4.63.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:27fdc65af8da6f88b9c6121c47a464cbe359fcfff7ff6fc2d37a1f395d755b78", size = 5133598, upload-time = "2026-05-14T12:03:25.168Z" },
+    { url = "https://files.pythonhosted.org/packages/62/f2/aa27c7f98db5b064883dadcc5283947e81e034de42e22a33675878d98b54/fonttools-4.63.0-cp312-cp312-win32.whl", hash = "sha256:af2fd1664d00a397d75f806985ddb36282091c2131a73a6485c23b4a34722263", size = 2292575, upload-time = "2026-05-14T12:03:27.496Z" },
+    { url = "https://files.pythonhosted.org/packages/87/36/cccb9bc2a6ab63d1b2980374f0dca72ce95ae267c9b4cfe77455bb70d0d4/fonttools-4.63.0-cp312-cp312-win_amd64.whl", hash = "sha256:59ac449f8cca9b4ffa08d2e7bbadad87ce710d69d1eda5c3c1ce579baa987272", size = 2343211, upload-time = "2026-05-14T12:03:30.057Z" },
+    { url = "https://files.pythonhosted.org/packages/0f/8d/d8fec3dcde2963f8c908fb315e5ff2cd0ac34f82394bbbf73a2aa5145ce3/fonttools-4.63.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:cd7e9857e5e63738b9d9fd707bc1f59c8b09e5177726d23664db393c59bb08bd", size = 2876062, upload-time = "2026-05-14T12:03:32.554Z" },
+    { url = "https://files.pythonhosted.org/packages/ef/71/d935dc54e4ff121bfdd11e08702db63a7e6f25af21d8a3d7b7212df53641/fonttools-4.63.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:c2a2a42198b696a6f48fad91709afb55176e66a5e566131219dba372fb7f8c59", size = 2424594, upload-time = "2026-05-14T12:03:34.86Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/40/e76320afa1df918e146155ef239b1719ee266092e96f5423bfd075affba1/fonttools-4.63.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1e874792a8212b44583ea02189d9e693906b2f78b261f372f95d6c563210ac1d", size = 5024840, upload-time = "2026-05-14T12:03:36.745Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/36/0b805d8c485f872f65a509cbe3b58a5d0d17bee855333b54a150c79d3061/fonttools-4.63.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:22135da48a348785c5e2d5d2d9d6bec5ed44adacbaeb9db12d9493bf6c6bfa68", size = 4975801, upload-time = "2026-05-14T12:03:38.833Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/26/2cee03d0aa083ab022da5c07aff9ed3f689da1defb81ad6917c9627896da/fonttools-4.63.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ccf41f2efdf56994d22d73bef4ced1052161958169428d06ba9724ea9e9a64be", size = 4965009, upload-time = "2026-05-14T12:03:41.494Z" },
+    { url = "https://files.pythonhosted.org/packages/7e/48/cc4b66d9058c0d0982c833fad10127c4b0e9324606aafa41382295ca4102/fonttools-4.63.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:9ced0bd02ac751dd6319b0da88aaef24414e3b0dbc32bb4f24944821a3741a27", size = 5105892, upload-time = "2026-05-14T12:03:43.525Z" },
+    { url = "https://files.pythonhosted.org/packages/d8/1f/a98a30a814b9ddef3a2e706025f90b9e0bc94890e6cb15254bc86547d11a/fonttools-4.63.0-cp313-cp313-win32.whl", hash = "sha256:85be818f5506e8a7753153def2c9550178f0ecae6a47b5e0e8dbb23f7cc90380", size = 2291313, upload-time = "2026-05-14T12:03:45.594Z" },
+    { url = "https://files.pythonhosted.org/packages/92/46/5177b01f3b4abfdd4409f31cca4ab279c9343a26efbe9ec78c97fc612e02/fonttools-4.63.0-cp313-cp313-win_amd64.whl", hash = "sha256:ba04cb5891d4c0c21b6da95eda8d7b090021508a294fff33464fc7d241e0856b", size = 2342299, upload-time = "2026-05-14T12:03:47.414Z" },
+    { url = "https://files.pythonhosted.org/packages/27/d2/23d25e3f247b328be58d04a4c9f894178a0d1eda7d42867cfb388adaf416/fonttools-4.63.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:fd1e3094f42d806d3d7c79162fc59e5910fcbe3a7360c385b8da969bc4493745", size = 2875338, upload-time = "2026-05-14T12:03:50.052Z" },
+    { url = "https://files.pythonhosted.org/packages/cd/58/7dfa0c761cb3b2964e2a84c4dc986c926a87de0cb9fb60d5b28ded3f2914/fonttools-4.63.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:6e528da43bc3791085f8cb6141b1d13e459226790240340fcbb4625649238b03", size = 2422661, upload-time = "2026-05-14T12:03:52.154Z" },
+    { url = "https://files.pythonhosted.org/packages/dd/87/64cfa18a7a1621d17b7f4502b2b0ed8a135a90c3db51ea590ee99043e76b/fonttools-4.63.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6b2248c5decb223562f7902ff6325077a073f608ee8e33e88ad88db734eb9f49", size = 5010526, upload-time = "2026-05-14T12:03:54.647Z" },
+    { url = "https://files.pythonhosted.org/packages/36/e1/a8933a72c45a87177fbde2696e0d0755c8c9062f8c077a961c6215fa27b1/fonttools-4.63.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:308f957cdeaf8abe4e5f2f124902ef405448af92c90f80e302a3b771c2e6116b", size = 4923946, upload-time = "2026-05-14T12:03:56.984Z" },
+    { url = "https://files.pythonhosted.org/packages/27/60/872e6e233b8c5e8b41413796ff18b7fe479661bd40147e071b450dfad7a1/fonttools-4.63.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:bf00f21eb5fb721dbaf73d1e9da6d02a1af7768f2ebcf9798be98beab8ba90f6", size = 4962489, upload-time = "2026-05-14T12:03:59.443Z" },
+    { url = "https://files.pythonhosted.org/packages/30/c4/83c24f2ec38b90cfda84bf4b1a1f49df80e84a1db4e7ac6e0d41bf23bc39/fonttools-4.63.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:c1aaa4b9c75798400ac043ce04d74e7830376c85095a5a6ed7cba2f17a266bf4", size = 5071870, upload-time = "2026-05-14T12:04:02.122Z" },
+    { url = "https://files.pythonhosted.org/packages/de/40/3ae22b60ff1d41ce0bd044b31238cdc72cef99f28b976f1e128ebd618c9b/fonttools-4.63.0-cp314-cp314-win32.whl", hash = "sha256:22693918177bd9ceabec4736d338045f357769416fc6b0b2508eefef75b08616", size = 2295026, upload-time = "2026-05-14T12:04:04.47Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/d4/98078064ccc76b45cb0f6c002452011e93c4bd26f6850344f0951cc1fe89/fonttools-4.63.0-cp314-cp314-win_amd64.whl", hash = "sha256:7d782fac32985914c351556f68ac0855391572bcd87de50e05970d3cd4c96fc5", size = 2347454, upload-time = "2026-05-14T12:04:06.752Z" },
+    { url = "https://files.pythonhosted.org/packages/49/4e/652d1580c5f4e39f7d103b0c793e4773129ad633dce4addd0cf4dfebde02/fonttools-4.63.0-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:6db5140a60a5d731d21ec076745b40a310607731b0a565b50776393188649001", size = 2958152, upload-time = "2026-05-14T12:04:08.706Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/55/ad864c9a9b219f552eb46b32cd7906c466e5a578ba0c3abfcc0fe7413eb6/fonttools-4.63.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:7d76edbff9014094dbf03bd2d074709dfa6ec7aba13d838c937a2b33d2d6a86e", size = 2460809, upload-time = "2026-05-14T12:04:10.783Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/2b/0aa8db70f18cf52e49b4ed5ecec68547f981160bf5ded3b5aed6faa0a6f9/fonttools-4.63.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0eac00b9118c3c2f87d272e45341871c5b3066baa3c86897fa634a7c3fb59096", size = 5148649, upload-time = "2026-05-14T12:04:12.747Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/63/18e4369c25043096f1048e0c9915951adc4f842bd81c6b18155824d6fa99/fonttools-4.63.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:51394295f1a51de8b5f30bdb1e1b9a4231536c7064ef5c6e211eec19fa36036f", size = 4932147, upload-time = "2026-05-14T12:04:14.806Z" },
+    { url = "https://files.pythonhosted.org/packages/a1/3f/67f3eac2ffd8a98446c5022f8ed3864eac878a5ff7af8df4c8286dba16cc/fonttools-4.63.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:9e12f105d2b6342c559c298afb674006bb2893afc7102dcf8a1b55b0486b4e40", size = 5027237, upload-time = "2026-05-14T12:04:17.675Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/ba/4e6214cb38a7b04779e97bb7636de9a5c7f20af7018d03dee0b64c08510a/fonttools-4.63.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:796f27556dbe094c4824f75ca85267e4df776c79036c8441469a4df37038c196", size = 5053933, upload-time = "2026-05-14T12:04:20.818Z" },
+    { url = "https://files.pythonhosted.org/packages/34/3b/214dcc19ee31d3d38fb5ad2755c11ef0514e5dc300bbaf41c0b69f393799/fonttools-4.63.0-cp314-cp314t-win32.whl", hash = "sha256:948428a275741f0b64b113c955425a953314f4b9ab9997f73a72c83e68e569c8", size = 2359326, upload-time = "2026-05-14T12:04:24.22Z" },
+    { url = "https://files.pythonhosted.org/packages/dd/1e/3ff1a9b523058c2eeb6a9d50f5574e2a738200d0d94107d5bc4105e8da3f/fonttools-4.63.0-cp314-cp314t-win_amd64.whl", hash = "sha256:6d4741eb179121cab9eea4cb2393d24492373a260d7945006358c08cfbf45419", size = 2425829, upload-time = "2026-05-14T12:04:26.829Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/47/c99d5268f354002ce80f8d029cd9d7d872969da1de8b93d32de4dc56d6f4/fonttools-4.63.0-py3-none-any.whl", hash = "sha256:445af2eab030a16b9171ea8bdda7ebf7d96bda2df88ee182a464252f6e05e20d", size = 1164562, upload-time = "2026-05-14T12:04:29.092Z" },
 ]
 
 [[package]]
 name = "fsspec"
-version = "2026.3.0"
+version = "2026.4.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/e1/cf/b50ddf667c15276a9ab15a70ef5f257564de271957933ffea49d2cdbcdfb/fsspec-2026.3.0.tar.gz", hash = "sha256:1ee6a0e28677557f8c2f994e3eea77db6392b4de9cd1f5d7a9e87a0ae9d01b41", size = 313547, upload-time = "2026-03-27T19:11:14.892Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/d5/8d/1c51c094345df128ca4a990d633fe1a0ff28726c9e6b3c41ba65087bba1d/fsspec-2026.4.0.tar.gz", hash = "sha256:301d8ac70ae90ef3ad05dcf94d6c3754a097f9b5fe4667d2787aa359ec7df7e4", size = 312760, upload-time = "2026-04-29T20:42:38.635Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d5/1f/5f4a3cd9e4440e9d9bc78ad0a91a1c8d46b4d429d5239ebe6793c9fe5c41/fsspec-2026.3.0-py3-none-any.whl", hash = "sha256:d2ceafaad1b3457968ed14efa28798162f1638dbb5d2a6868a2db002a5ee39a4", size = 202595, upload-time = "2026-03-27T19:11:13.595Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/0c/043d5e551459da400957a1395e0febbf771446ff34291afcbe3d8be2a279/fsspec-2026.4.0-py3-none-any.whl", hash = "sha256:11ef7bb35dab8a394fde6e608221d5cf3e8499401c249bebaeaad760a1a8dec2", size = 203402, upload-time = "2026-04-29T20:42:36.842Z" },
 ]
 
 [[package]]
@@ -509,11 +558,11 @@ wheels = [
 
 [[package]]
 name = "idna"
-version = "3.13"
+version = "3.15"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/ce/cc/762dfb036166873f0059f3b7de4565e1b5bc3d6f28a414c13da27e442f99/idna-3.13.tar.gz", hash = "sha256:585ea8fe5d69b9181ec1afba340451fba6ba764af97026f92a91d4eef164a242", size = 194210, upload-time = "2026-04-22T16:42:42.314Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/82/77/7b3966d0b9d1d31a36ddf1746926a11dface89a83409bf1483f0237aa758/idna-3.15.tar.gz", hash = "sha256:ca962446ea538f7092a95e057da437618e886f4d349216d2b1e294abfdb65fdc", size = 199245, upload-time = "2026-05-12T22:45:57.011Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/5d/13/ad7d7ca3808a898b4612b6fe93cde56b53f3034dcde235acb1f0e1df24c6/idna-3.13-py3-none-any.whl", hash = "sha256:892ea0cde124a99ce773decba204c5552b69c3c67ffd5f232eb7696135bc8bb3", size = 68629, upload-time = "2026-04-22T16:42:40.909Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/23/408243171aa9aaba178d3e2559159c24c1171a641aa83b67bdd3394ead8e/idna-3.15-py3-none-any.whl", hash = "sha256:048adeaf8c2d788c40fee287673ccaa74c24ffd8dcf09ffa555a2fbb59f10ac8", size = 72340, upload-time = "2026-05-12T22:45:55.733Z" },
 ]
 
 [[package]]
@@ -553,14 +602,14 @@ wheels = [
 
 [[package]]
 name = "jedi"
-version = "0.19.2"
+version = "0.20.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "parso" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/72/3a/79a912fbd4d8dd6fbb02bf69afd3bb72cf0c729bb3063c6f4498603db17a/jedi-0.19.2.tar.gz", hash = "sha256:4770dc3de41bde3966b02eb84fbcf557fb33cce26ad23da12c742fb50ecb11f0", size = 1231287, upload-time = "2024-11-11T01:41:42.873Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/46/b7/a3635f6a2d7cf5b5dd98064fc1d5fbbafcb25477bcea204a3a92145d158b/jedi-0.20.0.tar.gz", hash = "sha256:c3f4ccbd276696f4b19c54618d4fb18f9fc24b0aef02acf704b23f487daa1011", size = 3119416, upload-time = "2026-05-01T23:38:47.814Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/c0/5a/9cac0c82afec3d09ccd97c8b6502d48f165f9124db81b4bcb90b4af974ee/jedi-0.19.2-py2.py3-none-any.whl", hash = "sha256:a8ef22bde8490f57fe5c7681a3c83cb58874daf72b4784de3cce5b6ef6edb5b9", size = 1572278, upload-time = "2024-11-11T01:41:40.175Z" },
+    { url = "https://files.pythonhosted.org/packages/9a/93/242e2eab5fe682ffcb8b0084bde703a41d51e17ee0f3a31ff0d9d813620a/jedi-0.20.0-py2.py3-none-any.whl", hash = "sha256:7bdd9c2634f56713299976f4cbd59cb3fa92165cc5e05ea811fb253480728b67", size = 4884812, upload-time = "2026-05-01T23:38:43.919Z" },
 ]
 
 [[package]]
@@ -584,6 +633,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/7b/91/984aca2ec129e2757d1e4e3c81c3fcda9d0f85b74670a094cc443d9ee949/joblib-1.5.3-py3-none-any.whl", hash = "sha256:5fc3c5039fc5ca8c0276333a188bbd59d6b7ab37fe6632daa76bc7f9ec18e713", size = 309071, upload-time = "2025-12-15T08:41:44.973Z" },
 ]
 
+[[package]]
+name = "julius"
+version = "0.2.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "torch" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a1/19/c9e1596b5572c786b93428d0904280e964c930fae7e6c9368ed9e1b63922/julius-0.2.7.tar.gz", hash = "sha256:3c0f5f5306d7d6016fcc95196b274cae6f07e2c9596eed314e4e7641554fbb08", size = 59640, upload-time = "2022-09-19T16:13:34.2Z" }
+
 [[package]]
 name = "kiwisolver"
 version = "1.5.0"
@@ -905,14 +963,14 @@ wheels = [
 
 [[package]]
 name = "matplotlib-inline"
-version = "0.2.1"
+version = "0.2.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "traitlets" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/c7/74/97e72a36efd4ae2bccb3463284300f8953f199b5ffbc04cbbb0ec78f74b1/matplotlib_inline-0.2.1.tar.gz", hash = "sha256:e1ee949c340d771fc39e241ea75683deb94762c8fa5f2927ec57c83c4dffa9fe", size = 8110, upload-time = "2025-10-23T09:00:22.126Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/bd/c0/9f7c9a46090390368a4d7bcb76bb87a4a36c421e4c0792cdb53486ffac7a/matplotlib_inline-0.2.2.tar.gz", hash = "sha256:72f3fe8fce36b70d4a5b612f899090cd0401deddc4ea90e1572b9f4bfb058c79", size = 8150, upload-time = "2026-05-08T17:33:33.49Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/af/33/ee4519fa02ed11a94aef9559552f3b17bb863f2ecfe1a35dc7f548cde231/matplotlib_inline-0.2.1-py3-none-any.whl", hash = "sha256:d56ce5156ba6085e00a9d54fead6ed29a9c47e215cd1bba2e976ef39f5710a76", size = 9516, upload-time = "2025-10-23T09:00:20.675Z" },
+    { url = "https://files.pythonhosted.org/packages/41/09/5b161152e2d90f7b87f781c2e1267494aef9c32498df793f73ad0a0a494a/matplotlib_inline-0.2.2-py3-none-any.whl", hash = "sha256:3c821cf1c209f59fb2d2d64abbf5b23b67bcb2210d663f9918dd851c6da1fcf6", size = 9534, upload-time = "2026-05-08T17:33:32.055Z" },
 ]
 
 [[package]]
@@ -977,6 +1035,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/81/f2/08ace4142eb281c12701fc3b93a10795e4d4dc7f753911d836675050f886/msgpack-1.1.2-cp314-cp314t-win_arm64.whl", hash = "sha256:d99ef64f349d5ec3293688e91486c5fdb925ed03807f64d98d205d2713c60b46", size = 70868, upload-time = "2025-10-08T09:15:44.959Z" },
 ]
 
+[[package]]
+name = "mutagen"
+version = "1.47.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/81/e6/64bc71b74eef4b68e61eb921dcf72dabd9e4ec4af1e11891bbd312ccbb77/mutagen-1.47.0.tar.gz", hash = "sha256:719fadef0a978c31b4cf3c956261b3c58b6948b32023078a2117b1de09f0fc99", size = 1274186, upload-time = "2023-09-03T16:33:33.411Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b0/7a/620f945b96be1f6ee357d211d5bf74ab1b7fe72a9f1525aafbfe3aee6875/mutagen-1.47.0-py3-none-any.whl", hash = "sha256:edd96f50c5907a9539d8e5bba7245f62c9f520aef333d13392a79a4f70aca719", size = 194391, upload-time = "2023-09-03T16:33:29.955Z" },
+]
+
 [[package]]
 name = "networkx"
 version = "3.6.1"
@@ -1020,81 +1087,81 @@ wheels = [
 
 [[package]]
 name = "numpy"
-version = "2.4.4"
+version = "2.4.5"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/d7/9f/b8cef5bffa569759033adda9481211426f12f53299629b410340795c2514/numpy-2.4.4.tar.gz", hash = "sha256:2d390634c5182175533585cc89f3608a4682ccb173cc9bb940b2881c8d6f8fa0", size = 20731587, upload-time = "2026-03-29T13:22:01.298Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/50/8e/b8041bc719f056afd864478029d52214789341ac6583437b0ee5031e9530/numpy-2.4.5.tar.gz", hash = "sha256:ca670567a5683b7c1670ec03e0ddd5862e10934e92a70751d68d7b7b74ca7f9f", size = 20735669, upload-time = "2026-05-15T20:25:19.492Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ef/c6/4218570d8c8ecc9704b5157a3348e486e84ef4be0ed3e38218ab473c83d2/numpy-2.4.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f983334aea213c99992053ede6168500e5f086ce74fbc4acc3f2b00f5762e9db", size = 16976799, upload-time = "2026-03-29T13:18:15.438Z" },
-    { url = "https://files.pythonhosted.org/packages/dd/92/b4d922c4a5f5dab9ed44e6153908a5c665b71acf183a83b93b690996e39b/numpy-2.4.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:72944b19f2324114e9dc86a159787333b77874143efcf89a5167ef83cfee8af0", size = 14971552, upload-time = "2026-03-29T13:18:18.606Z" },
-    { url = "https://files.pythonhosted.org/packages/8a/dc/df98c095978fa6ee7b9a9387d1d58cbb3d232d0e69ad169a4ce784bde4fd/numpy-2.4.4-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:86b6f55f5a352b48d7fbfd2dbc3d5b780b2d79f4d3c121f33eb6efb22e9a2015", size = 5476566, upload-time = "2026-03-29T13:18:21.532Z" },
-    { url = "https://files.pythonhosted.org/packages/28/34/b3fdcec6e725409223dd27356bdf5a3c2cc2282e428218ecc9cb7acc9763/numpy-2.4.4-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:ba1f4fc670ed79f876f70082eff4f9583c15fb9a4b89d6188412de4d18ae2f40", size = 6806482, upload-time = "2026-03-29T13:18:23.634Z" },
-    { url = "https://files.pythonhosted.org/packages/68/62/63417c13aa35d57bee1337c67446761dc25ea6543130cf868eace6e8157b/numpy-2.4.4-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8a87ec22c87be071b6bdbd27920b129b94f2fc964358ce38f3822635a3e2e03d", size = 15973376, upload-time = "2026-03-29T13:18:26.677Z" },
-    { url = "https://files.pythonhosted.org/packages/cf/c5/9fcb7e0e69cef59cf10c746b84f7d58b08bc66a6b7d459783c5a4f6101a6/numpy-2.4.4-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:df3775294accfdd75f32c74ae39fcba920c9a378a2fc18a12b6820aa8c1fb502", size = 16925137, upload-time = "2026-03-29T13:18:30.14Z" },
-    { url = "https://files.pythonhosted.org/packages/7e/43/80020edacb3f84b9efdd1591120a4296462c23fd8db0dde1666f6ef66f13/numpy-2.4.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:0d4e437e295f18ec29bc79daf55e8a47a9113df44d66f702f02a293d93a2d6dd", size = 17329414, upload-time = "2026-03-29T13:18:33.733Z" },
-    { url = "https://files.pythonhosted.org/packages/fd/06/af0658593b18a5f73532d377188b964f239eb0894e664a6c12f484472f97/numpy-2.4.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:6aa3236c78803afbcb255045fbef97a9e25a1f6c9888357d205ddc42f4d6eba5", size = 18658397, upload-time = "2026-03-29T13:18:37.511Z" },
-    { url = "https://files.pythonhosted.org/packages/e6/ce/13a09ed65f5d0ce5c7dd0669250374c6e379910f97af2c08c57b0608eee4/numpy-2.4.4-cp311-cp311-win32.whl", hash = "sha256:30caa73029a225b2d40d9fae193e008e24b2026b7ee1a867b7ee8d96ca1a448e", size = 6239499, upload-time = "2026-03-29T13:18:40.372Z" },
-    { url = "https://files.pythonhosted.org/packages/bd/63/05d193dbb4b5eec1eca73822d80da98b511f8328ad4ae3ca4caf0f4db91d/numpy-2.4.4-cp311-cp311-win_amd64.whl", hash = "sha256:6bbe4eb67390b0a0265a2c25458f6b90a409d5d069f1041e6aff1e27e3d9a79e", size = 12614257, upload-time = "2026-03-29T13:18:42.95Z" },
-    { url = "https://files.pythonhosted.org/packages/87/c5/8168052f080c26fa984c413305012be54741c9d0d74abd7fbeeccae3889f/numpy-2.4.4-cp311-cp311-win_arm64.whl", hash = "sha256:fcfe2045fd2e8f3cb0ce9d4ba6dba6333b8fa05bb8a4939c908cd43322d14c7e", size = 10486775, upload-time = "2026-03-29T13:18:45.835Z" },
-    { url = "https://files.pythonhosted.org/packages/28/05/32396bec30fb2263770ee910142f49c1476d08e8ad41abf8403806b520ce/numpy-2.4.4-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:15716cfef24d3a9762e3acdf87e27f58dc823d1348f765bbea6bef8c639bfa1b", size = 16689272, upload-time = "2026-03-29T13:18:49.223Z" },
-    { url = "https://files.pythonhosted.org/packages/c5/f3/a983d28637bfcd763a9c7aafdb6d5c0ebf3d487d1e1459ffdb57e2f01117/numpy-2.4.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:23cbfd4c17357c81021f21540da84ee282b9c8fba38a03b7b9d09ba6b951421e", size = 14699573, upload-time = "2026-03-29T13:18:52.629Z" },
-    { url = "https://files.pythonhosted.org/packages/9b/fd/e5ecca1e78c05106d98028114f5c00d3eddb41207686b2b7de3e477b0e22/numpy-2.4.4-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:8b3b60bb7cba2c8c81837661c488637eee696f59a877788a396d33150c35d842", size = 5204782, upload-time = "2026-03-29T13:18:55.579Z" },
-    { url = "https://files.pythonhosted.org/packages/de/2f/702a4594413c1a8632092beae8aba00f1d67947389369b3777aed783fdca/numpy-2.4.4-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:e4a010c27ff6f210ff4c6ef34394cd61470d01014439b192ec22552ee867f2a8", size = 6552038, upload-time = "2026-03-29T13:18:57.769Z" },
-    { url = "https://files.pythonhosted.org/packages/7f/37/eed308a8f56cba4d1fdf467a4fc67ef4ff4bf1c888f5fc980481890104b1/numpy-2.4.4-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f9e75681b59ddaa5e659898085ae0eaea229d054f2ac0c7e563a62205a700121", size = 15670666, upload-time = "2026-03-29T13:19:00.341Z" },
-    { url = "https://files.pythonhosted.org/packages/0a/0d/0e3ecece05b7a7e87ab9fb587855548da437a061326fff64a223b6dcb78a/numpy-2.4.4-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:81f4a14bee47aec54f883e0cad2d73986640c1590eb9bfaaba7ad17394481e6e", size = 16645480, upload-time = "2026-03-29T13:19:03.63Z" },
-    { url = "https://files.pythonhosted.org/packages/34/49/f2312c154b82a286758ee2f1743336d50651f8b5195db18cdb63675ff649/numpy-2.4.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:62d6b0f03b694173f9fcb1fb317f7222fd0b0b103e784c6549f5e53a27718c44", size = 17020036, upload-time = "2026-03-29T13:19:07.428Z" },
-    { url = "https://files.pythonhosted.org/packages/7b/e9/736d17bd77f1b0ec4f9901aaec129c00d59f5d84d5e79bba540ef12c2330/numpy-2.4.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:fbc356aae7adf9e6336d336b9c8111d390a05df88f1805573ebb0807bd06fd1d", size = 18368643, upload-time = "2026-03-29T13:19:10.775Z" },
-    { url = "https://files.pythonhosted.org/packages/63/f6/d417977c5f519b17c8a5c3bc9e8304b0908b0e21136fe43bf628a1343914/numpy-2.4.4-cp312-cp312-win32.whl", hash = "sha256:0d35aea54ad1d420c812bfa0385c71cd7cc5bcf7c65fed95fc2cd02fe8c79827", size = 5961117, upload-time = "2026-03-29T13:19:13.464Z" },
-    { url = "https://files.pythonhosted.org/packages/2d/5b/e1deebf88ff431b01b7406ca3583ab2bbb90972bbe1c568732e49c844f7e/numpy-2.4.4-cp312-cp312-win_amd64.whl", hash = "sha256:b5f0362dc928a6ecd9db58868fca5e48485205e3855957bdedea308f8672ea4a", size = 12320584, upload-time = "2026-03-29T13:19:16.155Z" },
-    { url = "https://files.pythonhosted.org/packages/58/89/e4e856ac82a68c3ed64486a544977d0e7bdd18b8da75b78a577ca31c4395/numpy-2.4.4-cp312-cp312-win_arm64.whl", hash = "sha256:846300f379b5b12cc769334464656bc882e0735d27d9726568bc932fdc49d5ec", size = 10221450, upload-time = "2026-03-29T13:19:18.994Z" },
-    { url = "https://files.pythonhosted.org/packages/14/1d/d0a583ce4fefcc3308806a749a536c201ed6b5ad6e1322e227ee4848979d/numpy-2.4.4-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:08f2e31ed5e6f04b118e49821397f12767934cfdd12a1ce86a058f91e004ee50", size = 16684933, upload-time = "2026-03-29T13:19:22.47Z" },
-    { url = "https://files.pythonhosted.org/packages/c1/62/2b7a48fbb745d344742c0277f01286dead15f3f68e4f359fbfcf7b48f70f/numpy-2.4.4-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:e823b8b6edc81e747526f70f71a9c0a07ac4e7ad13020aa736bb7c9d67196115", size = 14694532, upload-time = "2026-03-29T13:19:25.581Z" },
-    { url = "https://files.pythonhosted.org/packages/e5/87/499737bfba066b4a3bebff24a8f1c5b2dee410b209bc6668c9be692580f0/numpy-2.4.4-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:4a19d9dba1a76618dd86b164d608566f393f8ec6ac7c44f0cc879011c45e65af", size = 5199661, upload-time = "2026-03-29T13:19:28.31Z" },
-    { url = "https://files.pythonhosted.org/packages/cd/da/464d551604320d1491bc345efed99b4b7034143a85787aab78d5691d5a0e/numpy-2.4.4-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:d2a8490669bfe99a233298348acc2d824d496dee0e66e31b66a6022c2ad74a5c", size = 6547539, upload-time = "2026-03-29T13:19:30.97Z" },
-    { url = "https://files.pythonhosted.org/packages/7d/90/8d23e3b0dafd024bf31bdec225b3bb5c2dbfa6912f8a53b8659f21216cbf/numpy-2.4.4-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:45dbed2ab436a9e826e302fcdcbe9133f9b0006e5af7168afb8963a6520da103", size = 15668806, upload-time = "2026-03-29T13:19:33.887Z" },
-    { url = "https://files.pythonhosted.org/packages/d1/73/a9d864e42a01896bb5974475438f16086be9ba1f0d19d0bb7a07427c4a8b/numpy-2.4.4-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c901b15172510173f5cb310eae652908340f8dede90fff9e3bf6c0d8dfd92f83", size = 16632682, upload-time = "2026-03-29T13:19:37.336Z" },
-    { url = "https://files.pythonhosted.org/packages/34/fb/14570d65c3bde4e202a031210475ae9cde9b7686a2e7dc97ee67d2833b35/numpy-2.4.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:99d838547ace2c4aace6c4f76e879ddfe02bb58a80c1549928477862b7a6d6ed", size = 17019810, upload-time = "2026-03-29T13:19:40.963Z" },
-    { url = "https://files.pythonhosted.org/packages/8a/77/2ba9d87081fd41f6d640c83f26fb7351e536b7ce6dd9061b6af5904e8e46/numpy-2.4.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:0aec54fd785890ecca25a6003fd9a5aed47ad607bbac5cd64f836ad8666f4959", size = 18357394, upload-time = "2026-03-29T13:19:44.859Z" },
-    { url = "https://files.pythonhosted.org/packages/a2/23/52666c9a41708b0853fa3b1a12c90da38c507a3074883823126d4e9d5b30/numpy-2.4.4-cp313-cp313-win32.whl", hash = "sha256:07077278157d02f65c43b1b26a3886bce886f95d20aabd11f87932750dfb14ed", size = 5959556, upload-time = "2026-03-29T13:19:47.661Z" },
-    { url = "https://files.pythonhosted.org/packages/57/fb/48649b4971cde70d817cf97a2a2fdc0b4d8308569f1dd2f2611959d2e0cf/numpy-2.4.4-cp313-cp313-win_amd64.whl", hash = "sha256:5c70f1cc1c4efbe316a572e2d8b9b9cc44e89b95f79ca3331553fbb63716e2bf", size = 12317311, upload-time = "2026-03-29T13:19:50.67Z" },
-    { url = "https://files.pythonhosted.org/packages/ba/d8/11490cddd564eb4de97b4579ef6bfe6a736cc07e94c1598590ae25415e01/numpy-2.4.4-cp313-cp313-win_arm64.whl", hash = "sha256:ef4059d6e5152fa1a39f888e344c73fdc926e1b2dd58c771d67b0acfbf2aa67d", size = 10222060, upload-time = "2026-03-29T13:19:54.229Z" },
-    { url = "https://files.pythonhosted.org/packages/99/5d/dab4339177a905aad3e2221c915b35202f1ec30d750dd2e5e9d9a72b804b/numpy-2.4.4-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:4bbc7f303d125971f60ec0aaad5e12c62d0d2c925f0ab1273debd0e4ba37aba5", size = 14822302, upload-time = "2026-03-29T13:19:57.585Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/e4/0564a65e7d3d97562ed6f9b0fd0fb0a6f559ee444092f105938b50043876/numpy-2.4.4-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:4d6d57903571f86180eb98f8f0c839fa9ebbfb031356d87f1361be91e433f5b7", size = 5327407, upload-time = "2026-03-29T13:20:00.601Z" },
-    { url = "https://files.pythonhosted.org/packages/29/8d/35a3a6ce5ad371afa58b4700f1c820f8f279948cca32524e0a695b0ded83/numpy-2.4.4-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:4636de7fd195197b7535f231b5de9e4b36d2c440b6e566d2e4e4746e6af0ca93", size = 6647631, upload-time = "2026-03-29T13:20:02.855Z" },
-    { url = "https://files.pythonhosted.org/packages/f4/da/477731acbd5a58a946c736edfdabb2ac5b34c3d08d1ba1a7b437fa0884df/numpy-2.4.4-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ad2e2ef14e0b04e544ea2fa0a36463f847f113d314aa02e5b402fdf910ef309e", size = 15727691, upload-time = "2026-03-29T13:20:06.004Z" },
-    { url = "https://files.pythonhosted.org/packages/e6/db/338535d9b152beabeb511579598418ba0212ce77cf9718edd70262cc4370/numpy-2.4.4-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5a285b3b96f951841799528cd1f4f01cd70e7e0204b4abebac9463eecfcf2a40", size = 16681241, upload-time = "2026-03-29T13:20:09.417Z" },
-    { url = "https://files.pythonhosted.org/packages/e2/a9/ad248e8f58beb7a0219b413c9c7d8151c5d285f7f946c3e26695bdbbe2df/numpy-2.4.4-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:f8474c4241bc18b750be2abea9d7a9ec84f46ef861dbacf86a4f6e043401f79e", size = 17085767, upload-time = "2026-03-29T13:20:13.126Z" },
-    { url = "https://files.pythonhosted.org/packages/b5/1a/3b88ccd3694681356f70da841630e4725a7264d6a885c8d442a697e1146b/numpy-2.4.4-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:4e874c976154687c1f71715b034739b45c7711bec81db01914770373d125e392", size = 18403169, upload-time = "2026-03-29T13:20:17.096Z" },
-    { url = "https://files.pythonhosted.org/packages/c2/c9/fcfd5d0639222c6eac7f304829b04892ef51c96a75d479214d77e3ce6e33/numpy-2.4.4-cp313-cp313t-win32.whl", hash = "sha256:9c585a1790d5436a5374bac930dad6ed244c046ed91b2b2a3634eb2971d21008", size = 6083477, upload-time = "2026-03-29T13:20:20.195Z" },
-    { url = "https://files.pythonhosted.org/packages/d5/e3/3938a61d1c538aaec8ed6fd6323f57b0c2d2d2219512434c5c878db76553/numpy-2.4.4-cp313-cp313t-win_amd64.whl", hash = "sha256:93e15038125dc1e5345d9b5b68aa7f996ec33b98118d18c6ca0d0b7d6198b7e8", size = 12457487, upload-time = "2026-03-29T13:20:22.946Z" },
-    { url = "https://files.pythonhosted.org/packages/97/6a/7e345032cc60501721ef94e0e30b60f6b0bd601f9174ebd36389a2b86d40/numpy-2.4.4-cp313-cp313t-win_arm64.whl", hash = "sha256:0dfd3f9d3adbe2920b68b5cd3d51444e13a10792ec7154cd0a2f6e74d4ab3233", size = 10292002, upload-time = "2026-03-29T13:20:25.909Z" },
-    { url = "https://files.pythonhosted.org/packages/6e/06/c54062f85f673dd5c04cbe2f14c3acb8c8b95e3384869bb8cc9bff8cb9df/numpy-2.4.4-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:f169b9a863d34f5d11b8698ead99febeaa17a13ca044961aa8e2662a6c7766a0", size = 16684353, upload-time = "2026-03-29T13:20:29.504Z" },
-    { url = "https://files.pythonhosted.org/packages/4c/39/8a320264a84404c74cc7e79715de85d6130fa07a0898f67fb5cd5bd79908/numpy-2.4.4-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:2483e4584a1cb3092da4470b38866634bafb223cbcd551ee047633fd2584599a", size = 14704914, upload-time = "2026-03-29T13:20:33.547Z" },
-    { url = "https://files.pythonhosted.org/packages/91/fb/287076b2614e1d1044235f50f03748f31fa287e3dbe6abeb35cdfa351eca/numpy-2.4.4-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:2d19e6e2095506d1736b7d80595e0f252d76b89f5e715c35e06e937679ea7d7a", size = 5210005, upload-time = "2026-03-29T13:20:36.45Z" },
-    { url = "https://files.pythonhosted.org/packages/63/eb/fcc338595309910de6ecabfcef2419a9ce24399680bfb149421fa2df1280/numpy-2.4.4-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:6a246d5914aa1c820c9443ddcee9c02bec3e203b0c080349533fae17727dfd1b", size = 6544974, upload-time = "2026-03-29T13:20:39.014Z" },
-    { url = "https://files.pythonhosted.org/packages/44/5d/e7e9044032a716cdfaa3fba27a8e874bf1c5f1912a1ddd4ed071bf8a14a6/numpy-2.4.4-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:989824e9faf85f96ec9c7761cd8d29c531ad857bfa1daa930cba85baaecf1a9a", size = 15684591, upload-time = "2026-03-29T13:20:42.146Z" },
-    { url = "https://files.pythonhosted.org/packages/98/7c/21252050676612625449b4807d6b695b9ce8a7c9e1c197ee6216c8a65c7c/numpy-2.4.4-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:27a8d92cd10f1382a67d7cf4db7ce18341b66438bdd9f691d7b0e48d104c2a9d", size = 16637700, upload-time = "2026-03-29T13:20:46.204Z" },
-    { url = "https://files.pythonhosted.org/packages/b1/29/56d2bbef9465db24ef25393383d761a1af4f446a1df9b8cded4fe3a5a5d7/numpy-2.4.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:e44319a2953c738205bf3354537979eaa3998ed673395b964c1176083dd46252", size = 17035781, upload-time = "2026-03-29T13:20:50.242Z" },
-    { url = "https://files.pythonhosted.org/packages/e3/2b/a35a6d7589d21f44cea7d0a98de5ddcbb3d421b2622a5c96b1edf18707c3/numpy-2.4.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:e892aff75639bbef0d2a2cfd55535510df26ff92f63c92cd84ef8d4ba5a5557f", size = 18362959, upload-time = "2026-03-29T13:20:54.019Z" },
-    { url = "https://files.pythonhosted.org/packages/64/c9/d52ec581f2390e0f5f85cbfd80fb83d965fc15e9f0e1aec2195faa142cde/numpy-2.4.4-cp314-cp314-win32.whl", hash = "sha256:1378871da56ca8943c2ba674530924bb8ca40cd228358a3b5f302ad60cf875fc", size = 6008768, upload-time = "2026-03-29T13:20:56.912Z" },
-    { url = "https://files.pythonhosted.org/packages/fa/22/4cc31a62a6c7b74a8730e31a4274c5dc80e005751e277a2ce38e675e4923/numpy-2.4.4-cp314-cp314-win_amd64.whl", hash = "sha256:715d1c092715954784bc79e1174fc2a90093dc4dc84ea15eb14dad8abdcdeb74", size = 12449181, upload-time = "2026-03-29T13:20:59.548Z" },
-    { url = "https://files.pythonhosted.org/packages/70/2e/14cda6f4d8e396c612d1bf97f22958e92148801d7e4f110cabebdc0eef4b/numpy-2.4.4-cp314-cp314-win_arm64.whl", hash = "sha256:2c194dd721e54ecad9ad387c1d35e63dce5c4450c6dc7dd5611283dda239aabb", size = 10496035, upload-time = "2026-03-29T13:21:02.524Z" },
-    { url = "https://files.pythonhosted.org/packages/b1/e8/8fed8c8d848d7ecea092dc3469643f9d10bc3a134a815a3b033da1d2039b/numpy-2.4.4-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:2aa0613a5177c264ff5921051a5719d20095ea586ca88cc802c5c218d1c67d3e", size = 14824958, upload-time = "2026-03-29T13:21:05.671Z" },
-    { url = "https://files.pythonhosted.org/packages/05/1a/d8007a5138c179c2bf33ef44503e83d70434d2642877ee8fbb230e7c0548/numpy-2.4.4-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:42c16925aa5a02362f986765f9ebabf20de75cdefdca827d14315c568dcab113", size = 5330020, upload-time = "2026-03-29T13:21:08.635Z" },
-    { url = "https://files.pythonhosted.org/packages/99/64/ffb99ac6ae93faf117bcbd5c7ba48a7f45364a33e8e458545d3633615dda/numpy-2.4.4-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:874f200b2a981c647340f841730fc3a2b54c9d940566a3c4149099591e2c4c3d", size = 6650758, upload-time = "2026-03-29T13:21:10.949Z" },
-    { url = "https://files.pythonhosted.org/packages/6e/6e/795cc078b78a384052e73b2f6281ff7a700e9bf53bcce2ee579d4f6dd879/numpy-2.4.4-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c9b39d38a9bd2ae1becd7eac1303d031c5c110ad31f2b319c6e7d98b135c934d", size = 15729948, upload-time = "2026-03-29T13:21:14.047Z" },
-    { url = "https://files.pythonhosted.org/packages/5f/86/2acbda8cc2af5f3d7bfc791192863b9e3e19674da7b5e533fded124d1299/numpy-2.4.4-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b268594bccac7d7cf5844c7732e3f20c50921d94e36d7ec9b79e9857694b1b2f", size = 16679325, upload-time = "2026-03-29T13:21:17.561Z" },
-    { url = "https://files.pythonhosted.org/packages/bc/59/cafd83018f4aa55e0ac6fa92aa066c0a1877b77a615ceff1711c260ffae8/numpy-2.4.4-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:ac6b31e35612a26483e20750126d30d0941f949426974cace8e6b5c58a3657b0", size = 17084883, upload-time = "2026-03-29T13:21:21.106Z" },
-    { url = "https://files.pythonhosted.org/packages/f0/85/a42548db84e65ece46ab2caea3d3f78b416a47af387fcbb47ec28e660dc2/numpy-2.4.4-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:8e3ed142f2728df44263aaf5fb1f5b0b99f4070c553a0d7f033be65338329150", size = 18403474, upload-time = "2026-03-29T13:21:24.828Z" },
-    { url = "https://files.pythonhosted.org/packages/ed/ad/483d9e262f4b831000062e5d8a45e342166ec8aaa1195264982bca267e62/numpy-2.4.4-cp314-cp314t-win32.whl", hash = "sha256:dddbbd259598d7240b18c9d87c56a9d2fb3b02fe266f49a7c101532e78c1d871", size = 6155500, upload-time = "2026-03-29T13:21:28.205Z" },
-    { url = "https://files.pythonhosted.org/packages/c7/03/2fc4e14c7bd4ff2964b74ba90ecb8552540b6315f201df70f137faa5c589/numpy-2.4.4-cp314-cp314t-win_amd64.whl", hash = "sha256:a7164afb23be6e37ad90b2f10426149fd75aee07ca55653d2aa41e66c4ef697e", size = 12637755, upload-time = "2026-03-29T13:21:31.107Z" },
-    { url = "https://files.pythonhosted.org/packages/58/78/548fb8e07b1a341746bfbecb32f2c268470f45fa028aacdbd10d9bc73aab/numpy-2.4.4-cp314-cp314t-win_arm64.whl", hash = "sha256:ba203255017337d39f89bdd58417f03c4426f12beed0440cfd933cb15f8669c7", size = 10566643, upload-time = "2026-03-29T13:21:34.339Z" },
-    { url = "https://files.pythonhosted.org/packages/6b/33/8fae8f964a4f63ed528264ddf25d2b683d0b663e3cba26961eb838a7c1bd/numpy-2.4.4-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:58c8b5929fcb8287cbd6f0a3fae19c6e03a5c48402ae792962ac465224a629a4", size = 16854491, upload-time = "2026-03-29T13:21:38.03Z" },
-    { url = "https://files.pythonhosted.org/packages/bc/d0/1aabee441380b981cf8cdda3ae7a46aa827d1b5a8cce84d14598bc94d6d9/numpy-2.4.4-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:eea7ac5d2dce4189771cedb559c738a71512768210dc4e4753b107a2048b3d0e", size = 14895830, upload-time = "2026-03-29T13:21:41.509Z" },
-    { url = "https://files.pythonhosted.org/packages/a5/b8/aafb0d1065416894fccf4df6b49ef22b8db045187949545bced89c034b8e/numpy-2.4.4-pp311-pypy311_pp73-macosx_14_0_arm64.whl", hash = "sha256:51fc224f7ca4d92656d5a5eb315f12eb5fe2c97a66249aa7b5f562528a3be38c", size = 5400927, upload-time = "2026-03-29T13:21:44.747Z" },
-    { url = "https://files.pythonhosted.org/packages/d6/77/063baa20b08b431038c7f9ff5435540c7b7265c78cf56012a483019ca72d/numpy-2.4.4-pp311-pypy311_pp73-macosx_14_0_x86_64.whl", hash = "sha256:28a650663f7314afc3e6ec620f44f333c386aad9f6fc472030865dc0ebb26ee3", size = 6715557, upload-time = "2026-03-29T13:21:47.406Z" },
-    { url = "https://files.pythonhosted.org/packages/c7/a8/379542d45a14f149444c5c4c4e7714707239ce9cc1de8c2803958889da14/numpy-2.4.4-pp311-pypy311_pp73-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:19710a9ca9992d7174e9c52f643d4272dcd1558c5f7af7f6f8190f633bd651a7", size = 15804253, upload-time = "2026-03-29T13:21:50.753Z" },
-    { url = "https://files.pythonhosted.org/packages/a2/c8/f0a45426d6d21e7ea3310a15cf90c43a14d9232c31a837702dba437f3373/numpy-2.4.4-pp311-pypy311_pp73-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9b2aec6af35c113b05695ebb5749a787acd63cafc83086a05771d1e1cd1e555f", size = 16753552, upload-time = "2026-03-29T13:21:54.344Z" },
-    { url = "https://files.pythonhosted.org/packages/04/74/f4c001f4714c3ad9ce037e18cf2b9c64871a84951eaa0baf683a9ca9301c/numpy-2.4.4-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:f2cf083b324a467e1ab358c105f6cad5ea950f50524668a80c486ff1db24e119", size = 12509075, upload-time = "2026-03-29T13:21:57.644Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/44/1383ee4d1e916a9e610e46c876b5c83ea023526117d23cd911983929ec34/numpy-2.4.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3176dc8ff71dbb593606f91a69ad0c3cd3303c7eb546af477370ab9edf760288", size = 16969261, upload-time = "2026-05-15T20:22:23.036Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/61/54bacfbec7550bc398e6b6d9a861db35d64f75844e1d7920f5722c3cd5e7/numpy-2.4.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1811150e5148f5a01a7cc282cb2f489b4a3050a773e173adb480e507bad3a3d7", size = 14964009, upload-time = "2026-05-15T20:22:25.819Z" },
+    { url = "https://files.pythonhosted.org/packages/7a/55/fe86c64561761f185339c26001164a2687bd4787af681e961431abd2d534/numpy-2.4.5-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:0d63a780070871210853ba01e90b88f9b85cf2abf63a7f143d5127189265ddf6", size = 5469106, upload-time = "2026-05-15T20:22:28.13Z" },
+    { url = "https://files.pythonhosted.org/packages/2f/74/cf29b8317627f0e3aa2c9fb332d386bd734308cecd9e07da9f407d9ce0c3/numpy-2.4.5-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:0c6919cefafb3b76cd46a89dbb203bf1dd95529d2a6d09fef2d325d95d6a79d8", size = 6798945, upload-time = "2026-05-15T20:22:30.061Z" },
+    { url = "https://files.pythonhosted.org/packages/80/a9/b61730a17fa87d5abb13ce560a1b4ce3485d37a13e03eb7b414e598e72f8/numpy-2.4.5-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d51efede1e58e8b11877536a5518f60e318d8ff69b89ad7b38ee5e431b24d772", size = 15967025, upload-time = "2026-05-15T20:22:32.328Z" },
+    { url = "https://files.pythonhosted.org/packages/03/39/70bcd187eb4d223c21fde02c2bdfbffbffef3288cbb3947c04c74ae39a08/numpy-2.4.5-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:07ce7e74da92d7c71b5df157b9758bcdd53d7fea10602154de3afd2b3ddc34dd", size = 16918685, upload-time = "2026-05-15T20:22:34.759Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/31/400fd1315bbe228af3937cf8a74e32023df6217af36077919d00adc382e4/numpy-2.4.5-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:d7828234a13185effb34979e146f9921f2a65dfbbe215e6dbb57d6478fc8e059", size = 17322963, upload-time = "2026-05-15T20:22:37.557Z" },
+    { url = "https://files.pythonhosted.org/packages/18/6a/bbbafb657e6f6ee826b4ecdb8722a2e0aae4a981888eaf59eae6a535cc13/numpy-2.4.5-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:f96083adc3dfc1bbf778f2c79654d88115fa07074c97cb724fe9508f12d91c55", size = 18651594, upload-time = "2026-05-15T20:22:40.449Z" },
+    { url = "https://files.pythonhosted.org/packages/de/0c/857a515154a2a18b0dfae04089600d166d352d473ec17a0680d879582d06/numpy-2.4.5-cp311-cp311-win32.whl", hash = "sha256:4ed78c904a638b6e5d7cd4db90c06fca5fc6ec2f28d258305368f454a50e79cf", size = 6233849, upload-time = "2026-05-15T20:22:43.139Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/66/d215f3fb93541617adb5d58b3b9508e8a6413e499711e0adc0b80bcb445d/numpy-2.4.5-cp311-cp311-win_amd64.whl", hash = "sha256:079b0fad6f2899b23c5da89792b5409d2d83fc83e8bd5c2299cc9c397a264864", size = 12608238, upload-time = "2026-05-15T20:22:45.229Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/c4/611d66d3fcfa931954d37a19ce5575f3283d023e89ff0df6ad43b334ae9c/numpy-2.4.5-cp311-cp311-win_arm64.whl", hash = "sha256:d6c78e260b53affe9b395a9d54fc61f101f9521c4d9452c7e9e3718b19e2215b", size = 10479452, upload-time = "2026-05-15T20:22:47.962Z" },
+    { url = "https://files.pythonhosted.org/packages/6c/18/3275231e98620002681c922e792db04d72c356e9d8073c387344fc0e4ff1/numpy-2.4.5-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:654fb8674b61b1c4bd568f944d13a908566fdcb0d797303521d4149d16da05ef", size = 16689166, upload-time = "2026-05-15T20:22:50.761Z" },
+    { url = "https://files.pythonhosted.org/packages/db/23/000aab6a16bdec53307f0f72546b57a3ac9266a62d8c257bee97d85fd078/numpy-2.4.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:4cd9f6fa7ce10dc4627f2bb81dd9075dab67e94632e04c2b638e12575ddaa862", size = 14699514, upload-time = "2026-05-15T20:22:53.678Z" },
+    { url = "https://files.pythonhosted.org/packages/47/cc/ddaf3af9c46966fef5be879256f213d85a0c56c75d07a3b7defec7cf6b4c/numpy-2.4.5-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:4f5bc96d35d94e4ceab8b38a92241b4611e95dc44e63b9f1fa2a331858ee3507", size = 5204601, upload-time = "2026-05-15T20:22:56.257Z" },
+    { url = "https://files.pythonhosted.org/packages/07/ea/627fadd11959b3c7759008f34c92a35af8ff942dd8284a66ced648bbe516/numpy-2.4.5-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:4bb33e900ee81730ad77a258965134aa8ceac805124f7e5229347beda4b8d0aa", size = 6551360, upload-time = "2026-05-15T20:22:58.334Z" },
+    { url = "https://files.pythonhosted.org/packages/a1/47/0728b986b8682d742ff68c16baa5af9d185484abfc635c5cc700f44e62be/numpy-2.4.5-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:32f8f852273ef32b291201ac2a2c97629c4a1ee8632bb670e3443eaa09fc2e72", size = 15671157, upload-time = "2026-05-15T20:23:01.081Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/0b/b905ae82d9419dc38123523862db64978ca2954b69609c3ae8fdaca1084c/numpy-2.4.5-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:685681e956fc8dcb75adc6ff26694e1dfd738b24bd8d4696c51ca0110157f912", size = 16645703, upload-time = "2026-05-15T20:23:04.358Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/24/e27fc3f5236b4118ed9eed67111675f5c61a07ea333acec87c869c3b359d/numpy-2.4.5-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6f64dd84b277a737eb59513f6b9bb6195bf41ab11941ef15b2562dbab43fa8ef", size = 17021018, upload-time = "2026-05-15T20:23:07.021Z" },
+    { url = "https://files.pythonhosted.org/packages/d3/a7/9041af38d527ab80a06a93570a77e29425b41507ad41f6acf5da78cfb4a4/numpy-2.4.5-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:b42d9496f79e3a728192f05a42d86e36163217b7cdecb3813d0028a0aa6b72d7", size = 18368768, upload-time = "2026-05-15T20:23:09.44Z" },
+    { url = "https://files.pythonhosted.org/packages/49/82/326a014442f32c2663434fd424d9298791f47f8a0f17585ad60519a5606e/numpy-2.4.5-cp312-cp312-win32.whl", hash = "sha256:86d980970f5110595ca14855768073b08585fc1acc36895de303e039e7dee4a5", size = 5962819, upload-time = "2026-05-15T20:23:11.631Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/f0/cbf5d391b0b3a5e8cad264603e2fae256b0bde8ce43566b13b78faedc659/numpy-2.4.5-cp312-cp312-win_amd64.whl", hash = "sha256:3333dba6a4e611d666f69e177ba8fe4140366ff681a5feb2374d3fd4fff3acb6", size = 12321621, upload-time = "2026-05-15T20:23:14.305Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/d0/0f18909d9bc37a5f3f969fc737d2bb5df9f2ff295f71b467e6f52a0d6c4e/numpy-2.4.5-cp312-cp312-win_arm64.whl", hash = "sha256:4593d197270b894efeb538dcbe227e4bcf1c77f88c4c6bf933ead812cfaa4453", size = 10221430, upload-time = "2026-05-15T20:23:16.887Z" },
+    { url = "https://files.pythonhosted.org/packages/e3/a4/fb50657c7cab297bf34edcd60a074cb0647f61771430d6363575274160fe/numpy-2.4.5-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:1ef248460b645c102026b82337cc4e88231909c66dd77b59ec6d6cac7e44f277", size = 16684760, upload-time = "2026-05-15T20:23:19.436Z" },
+    { url = "https://files.pythonhosted.org/packages/3e/43/87e731299b9408eda705b3b9cb31c7bceb9347d2af9cbb16b2b1e4b5bc0f/numpy-2.4.5-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:4603622bdcdbf8dccb1d9d5b21d16a7aa4e473ae6c8e14048d846fd4ca2907a0", size = 14694117, upload-time = "2026-05-15T20:23:21.832Z" },
+    { url = "https://files.pythonhosted.org/packages/a9/c7/0b2bb8acea222e9dd6e582afc2bc553b89b8833cbdccc68e68f050fb31f8/numpy-2.4.5-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:6c18d49c67689c562854b53fdc433b93e47c12952aa6fa6d59f185e1a5992419", size = 5199141, upload-time = "2026-05-15T20:23:24.066Z" },
+    { url = "https://files.pythonhosted.org/packages/39/60/b6972b5d47033d90000f0097c81a98b9486589a2d7003bf725bff275cb0d/numpy-2.4.5-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:b1c663ddc641f4192e90511bec61a09bc231e3bbdb996cdc6edbcaa0e528d685", size = 6546954, upload-time = "2026-05-15T20:23:26.099Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/e9/ed667cb12c11ca0adde431f685d3a5dd78e6f78b27228c581c8415198e9e/numpy-2.4.5-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:93793222b524f692f12b2f8752ce8b1d9d9125b2bfd5dbf0fb69c92c5e1ce86c", size = 15669430, upload-time = "2026-05-15T20:23:28.147Z" },
+    { url = "https://files.pythonhosted.org/packages/44/e5/679f6ffeb01294b0008e5ada4a113cb47617bc0e1819a529fd7973c6d7f4/numpy-2.4.5-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1616bde34b2bcba2fa9bde06217ce00da4f3d1bdfb264d54525a99e8fe170d83", size = 16633390, upload-time = "2026-05-15T20:23:31.622Z" },
+    { url = "https://files.pythonhosted.org/packages/36/46/42bfffc9a780ec902ccd7470d3219192ee82b7b442710307dd85b4d121b0/numpy-2.4.5-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:09d7d97da1c2c62f4818b3e150a57572ff8dcf1cf5ac501aac832ffd4ebd9566", size = 17020709, upload-time = "2026-05-15T20:23:34.08Z" },
+    { url = "https://files.pythonhosted.org/packages/44/00/3e840bfee0cc6cec22209f2c97057f26eeb30de031e4933b4dfc0395416c/numpy-2.4.5-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:2d68d0b355ab2e39fe0de59001d7151dfdbbb880ef67baeed806661e03df5097", size = 18357818, upload-time = "2026-05-15T20:23:36.965Z" },
+    { url = "https://files.pythonhosted.org/packages/72/cb/3447b400b9da84134575486f0f656541559b00d4b262477bce9b678bbca8/numpy-2.4.5-cp313-cp313-win32.whl", hash = "sha256:fe28b64777ddfa0eca9b5f51474034ebe3dcb8324f48f27b28f479085673ae33", size = 5961114, upload-time = "2026-05-15T20:23:39.586Z" },
+    { url = "https://files.pythonhosted.org/packages/28/f9/a90d2220ffcdc0798f5d55bb5d5463cd6254ec9ef43f384dae80217d7a2f/numpy-2.4.5-cp313-cp313-win_amd64.whl", hash = "sha256:fb4a6c9c537d6ccec9cc4aeae4261bd3cc79b070c67ddc0646f5b1c07fddde42", size = 12318553, upload-time = "2026-05-15T20:23:41.436Z" },
+    { url = "https://files.pythonhosted.org/packages/b8/c9/96f531fb3234545315152d34efdf3de7daee81254448447eb619e8d16967/numpy-2.4.5-cp313-cp313-win_arm64.whl", hash = "sha256:6d7df2da2e7ea0624a43aa368104b3a3ce14aae98ad4bb2c9a93fecef76f1c97", size = 10222200, upload-time = "2026-05-15T20:23:43.681Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/f4/a291caab5a3c520babf93ff77c54fd5fdb1ebbc3296cee2eb2146ce773b1/numpy-2.4.5-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:2a235607a18df941760a695927051af4b1cd5d3ee85840d0e2af816785771feb", size = 14821438, upload-time = "2026-05-15T20:23:45.911Z" },
+    { url = "https://files.pythonhosted.org/packages/85/26/13dbb1159b864370568e7309063fd72667984df89db74e9caeb175d067c7/numpy-2.4.5-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:58dcf64969d870f36bc7fbd557d2617e997db7dc06261b6e3327148ea460d0a4", size = 5326663, upload-time = "2026-05-15T20:23:48.18Z" },
+    { url = "https://files.pythonhosted.org/packages/7c/99/d233408072a0e019e2288e27edd23f7d572ccd4a73d1539baa3270ede85d/numpy-2.4.5-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:235f54b0156274d8fa3155db3ed6d2f401c7e8f3367c90db0a12f02a58fde6ed", size = 6646874, upload-time = "2026-05-15T20:23:49.856Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/00/eeb6f193dfe767725e952e0464f3e51f44145c5dd261cd7389aa36ac0713/numpy-2.4.5-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ef3b5bb65437a3555c648e706475db01c645559ca80dc8b03e4f202ea757e0d6", size = 15728147, upload-time = "2026-05-15T20:23:51.655Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/c9/b8ed039f1fde1b13a8807c893e7e2f9432a379f4d6401edecf0028da5b2c/numpy-2.4.5-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7f09a7e5f017d7098c66522097c96257411c9620c0926212200d66bc8cee3976", size = 16681770, upload-time = "2026-05-15T20:23:53.933Z" },
+    { url = "https://files.pythonhosted.org/packages/11/5b/0198ef6cb7016eca6d895d392106012138127fab23f46637e76d5e25c9f5/numpy-2.4.5-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:993a88d8fdd8554466a8765cd8bacd97ba56b70ca6b0a04bcdca77f5afed4222", size = 17086218, upload-time = "2026-05-15T20:23:56.646Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/fe/8821f3cfc660ae84c92ee158505941874b62c56a42e035a41425228cd8cf/numpy-2.4.5-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:84f58bed609b5669f5ad3d597901a4f1f86ee5b3c3708aaa55f05b4fe6e0f656", size = 18403542, upload-time = "2026-05-15T20:23:59.173Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/00/e64ecaf498865e7b091f57658b2c522503e5d1b70e43b807f5f8247e1d88/numpy-2.4.5-cp313-cp313t-win32.whl", hash = "sha256:7200c58f3f933ca61e66346667dcc8510bb111995e9ce15398a731e6a4afa4bb", size = 6084903, upload-time = "2026-05-15T20:24:01.506Z" },
+    { url = "https://files.pythonhosted.org/packages/20/c0/354997dedaf74e8311c2cf9a6027b476fd8d424cb92189cc0ae2b25f501c/numpy-2.4.5-cp313-cp313t-win_amd64.whl", hash = "sha256:c26c71080d35db5002102f5d9ff614d45de02aa1f7802943e691e063e5ee93bc", size = 12458420, upload-time = "2026-05-15T20:24:03.735Z" },
+    { url = "https://files.pythonhosted.org/packages/66/dc/917ee5ea4a31ca1a6e4c9a85386477efa318dcc60db257c5ef4adda096c1/numpy-2.4.5-cp313-cp313t-win_arm64.whl", hash = "sha256:2caa576d1707b275cba1aeb60a5c50daa6fa2a3f28ecb08123bc05fd439005db", size = 10291826, upload-time = "2026-05-15T20:24:06.535Z" },
+    { url = "https://files.pythonhosted.org/packages/ca/c1/3be0bf102fc17cff5bd142e3be0bfffabec6fa46da0a462396c76b0765d0/numpy-2.4.5-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:889ca2c072315de638a5194a772aa1fa2df92bdd6175f6a222d4784040424b61", size = 16683455, upload-time = "2026-05-15T20:24:08.988Z" },
+    { url = "https://files.pythonhosted.org/packages/e8/3e/0742d724901fa36bc54b338c6e62e463a7601180da896aa44978f0adf004/numpy-2.4.5-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:89e89304fb1f8c3f0ecfa4a7d48f311dd79771336a940e920159d643d1307e77", size = 14704577, upload-time = "2026-05-15T20:24:11.542Z" },
+    { url = "https://files.pythonhosted.org/packages/25/1c/196c610ff4c6782d697ba780ebdc1616be143213701bf22c1a270f3bf7dd/numpy-2.4.5-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:144fcc5a3a17679b2b82543b4a2d8dd29937230a7af13232b5f753872feb6361", size = 5209756, upload-time = "2026-05-15T20:24:14.091Z" },
+    { url = "https://files.pythonhosted.org/packages/52/c0/23fb1bc506f774e03db66219a2830e720f4d3dbcaaddf855a7ff7bb6d96f/numpy-2.4.5-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:398bb16772b265b9fa5c07b07072646ea97137c10ffb62a9a087b277fc825c29", size = 6543937, upload-time = "2026-05-15T20:24:16.223Z" },
+    { url = "https://files.pythonhosted.org/packages/9f/49/db4662c26e68520afcc84d672a6f9f5294063dee0e57a46d61afdaa7f9ed/numpy-2.4.5-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:fb352e7b8876da1249e72254736d6c58c505fa4e58a3d7e30efca241ca9ca9ce", size = 15685292, upload-time = "2026-05-15T20:24:17.978Z" },
+    { url = "https://files.pythonhosted.org/packages/43/80/1315439acedd8398319bac177d6de3d48ab39c62cc0c810f74f0a9a73996/numpy-2.4.5-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7341b08ff8124d7353939778e2707b8732d03c78c1c30e0815aba2dacbe1245a", size = 16638528, upload-time = "2026-05-15T20:24:20.478Z" },
+    { url = "https://files.pythonhosted.org/packages/56/81/364388600932618fe735d97fdd2437cb8dd87a23377ac11d8b9d5db098b7/numpy-2.4.5-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:deb01226f012539f3945261ffe1c10aec081a0fa0a5c925419933c70f3ae2d23", size = 17036709, upload-time = "2026-05-15T20:24:22.949Z" },
+    { url = "https://files.pythonhosted.org/packages/32/4a/a1185b18a94a6d9587e54b437e7d0ba36ecf6e614f1bea03f5249912c64e/numpy-2.4.5-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:d888bdf7335f76878c3c7b264ac1ff089863e211ec81249f9fb5795c2183dc25", size = 18363254, upload-time = "2026-05-15T20:24:25.402Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/8e/95c1d2ed15ae97750ede8c8a0ac487c9c01207afff430f47078b1d9d7dc5/numpy-2.4.5-cp314-cp314-win32.whl", hash = "sha256:15f90d1256e9b2320aff24fde44815b787ab6d7c49a1a11bfd8138b321c5f080", size = 6010184, upload-time = "2026-05-15T20:24:27.852Z" },
+    { url = "https://files.pythonhosted.org/packages/aa/92/d063df4d63d988b20d881856c74df76c0c1786229bb870f3a52af0981d4d/numpy-2.4.5-cp314-cp314-win_amd64.whl", hash = "sha256:4bd2cd4ef9c0afa87de73723c0a33c0edff62143e1432917458e26d3d195d87f", size = 12450344, upload-time = "2026-05-15T20:24:29.856Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/64/c0ae481f7c3b2f85869bcd8fc5d30aa7c96b394162eef9c9315957f115c5/numpy-2.4.5-cp314-cp314-win_arm64.whl", hash = "sha256:db304568c650e9d7039744d3575d0d287754debb2057d7c7b8cdfdc2c487a957", size = 10495674, upload-time = "2026-05-15T20:24:32.352Z" },
+    { url = "https://files.pythonhosted.org/packages/57/89/c5a4c677acf17aa50ba09a15e61812f90baac42bb6ca38d112e005858351/numpy-2.4.5-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:6de2883e0d2c63eae1bab1a84b390dca74aabb3d20ea1f5d58f360853c83abf3", size = 14824078, upload-time = "2026-05-15T20:24:34.669Z" },
+    { url = "https://files.pythonhosted.org/packages/e7/52/57e7144284f6b51ba93523e495ff239260b1ecd5257e3700a436332e5688/numpy-2.4.5-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:06760fe73ae5005008748d182de612c733542af3cde063d532cd2127561b27be", size = 5329246, upload-time = "2026-05-15T20:24:36.957Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/b3/09dbce80fd4a7db4318f2fc01eec0ae76f29306442b5a32d4b811d082cdf/numpy-2.4.5-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:4b51a01745cb04cc19278482207444b4d30728ce91c28d27a3bfae5fc6ff24c7", size = 6649877, upload-time = "2026-05-15T20:24:38.861Z" },
+    { url = "https://files.pythonhosted.org/packages/30/c2/dbdb23e82d540b757690ef13f011c386fca6a63848eec6136baf8ce7cbed/numpy-2.4.5-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9a05636d7937d0936f271e5ba957fa8d746b5be3c2025caa1a2508f4fe521d40", size = 15730534, upload-time = "2026-05-15T20:24:41.168Z" },
+    { url = "https://files.pythonhosted.org/packages/c4/bd/68f6e9b3c20decf40ac06708a7b506757e3a8588efed32988d1b747316be/numpy-2.4.5-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:14b86f56048ed09c3bbe48962a7dff077c2fd3274f8cf981800f3b38eac49cc3", size = 16679741, upload-time = "2026-05-15T20:24:44.874Z" },
+    { url = "https://files.pythonhosted.org/packages/39/1d/0fcac0b6b4ea1b50ca8fca05a34bed5c8d56e34c1cb5ffb04cf76109ac3c/numpy-2.4.5-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:130d58151c4db23e9fa860b84784e219a3aa3e030acc88a493ea37006c4dfd4c", size = 17085598, upload-time = "2026-05-15T20:24:47.603Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/e8/a472b2564cf6cc498ad7aa9741d9832648221b8ab8cc0dbef41faa248ede/numpy-2.4.5-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:d475afc8cbe935ff5944f753d863bba774d7f4e1feaaa4102901e3e053ca5963", size = 18403855, upload-time = "2026-05-15T20:24:50.474Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/a4/da82196f8cc4bd28ecf17bd57008c84f3d4696caf06753d9bad45e4ad749/numpy-2.4.5-cp314-cp314t-win32.whl", hash = "sha256:27f4a6dc26353a860b348961b9aa9e009835688b435cfa105e873b8dc2c726f5", size = 6156900, upload-time = "2026-05-15T20:24:53.134Z" },
+    { url = "https://files.pythonhosted.org/packages/98/31/860959b91a73d9a085006554fa3850da51a7ffab64599bac5097243438ab/numpy-2.4.5-cp314-cp314t-win_amd64.whl", hash = "sha256:76ac6e90f5e226011c88f9b7040a4bcae612518bc7e9adc127e697a13b28ad1a", size = 12638906, upload-time = "2026-05-15T20:24:55.009Z" },
+    { url = "https://files.pythonhosted.org/packages/9e/2a/bbd3097913083ad07c0f28fc9629666221fc18923e17ce97ae22a5dccdd6/numpy-2.4.5-cp314-cp314t-win_arm64.whl", hash = "sha256:7c392e2c1bf596701d3c6832be7567eab5d5b0a13865036c33365ee097d37f8b", size = 10565875, upload-time = "2026-05-15T20:24:57.425Z" },
+    { url = "https://files.pythonhosted.org/packages/fc/5d/9a644cfb841bc76b584afc3af1708b3bf6c5cb51fc84a7008246cd93b7b7/numpy-2.4.5-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:6bf0bfc1c2e1db972e30b6cd3d4861f477f3af908b27799b239dc3cbe3eb4b95", size = 16847544, upload-time = "2026-05-15T20:24:59.746Z" },
+    { url = "https://files.pythonhosted.org/packages/56/8f/4fe5e3ba76d858dae1fe79078818c0520447335be0082c0dedf82719cc08/numpy-2.4.5-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:73d664413fb97229149c4711ef56531a6fe8c15c1c2626b0bbe497b84c287e70", size = 14889039, upload-time = "2026-05-15T20:25:03.179Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/6f/79f195abf922ecc43e7d0eb6cc969462a71b524a35bcd1fa26b4a1d7406a/numpy-2.4.5-pp311-pypy311_pp73-macosx_14_0_arm64.whl", hash = "sha256:b35bee5ef99e8d227a07829bee2e864fcb65f7c157646fcd8ec8b4b45dd8b88f", size = 5394106, upload-time = "2026-05-15T20:25:05.659Z" },
+    { url = "https://files.pythonhosted.org/packages/58/6f/79cd6247205802bcbd10b40ea087e20ded526e10e9be224d34de832b216e/numpy-2.4.5-pp311-pypy311_pp73-macosx_14_0_x86_64.whl", hash = "sha256:02981d0fc9f9ce147643d552966d47f329a02f7ecb3b113e84207242f20dfa83", size = 6708718, upload-time = "2026-05-15T20:25:08.071Z" },
+    { url = "https://files.pythonhosted.org/packages/d7/22/5f378a9d4633c98f28c4709d4144b1a4630c5c09e109d2e781e2d26c8fe1/numpy-2.4.5-pp311-pypy311_pp73-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0e63caf31a1df06338ae63d999f7a33a675ced62eea9c9b02db4b1c1f45cff38", size = 15798292, upload-time = "2026-05-15T20:25:10.689Z" },
+    { url = "https://files.pythonhosted.org/packages/63/1c/cec582febef798c99888892d92dc1d28dfe29cb427c41f44d13d0dec208f/numpy-2.4.5-pp311-pypy311_pp73-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d8fc52b85a7b45e474be53eddf08e006d22e381a4e41bcde8e4aa08da0e7d198", size = 16747406, upload-time = "2026-05-15T20:25:13.879Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/dc/d358a16a6fec86cf736b8fbe67386044b3fa2aded1a80cff90e836799301/numpy-2.4.5-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:40c71d50a4da1a7c317af419461052d3911a5770bfc5fd55baf52cc45e7a2c20", size = 12504085, upload-time = "2026-05-15T20:25:16.667Z" },
 ]
 
 [[package]]
@@ -1234,71 +1301,71 @@ wheels = [
 
 [[package]]
 name = "pandas"
-version = "3.0.2"
+version = "3.0.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "numpy" },
     { name = "python-dateutil" },
     { name = "tzdata", marker = "sys_platform == 'emscripten' or sys_platform == 'win32'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/da/99/b342345300f13440fe9fe385c3c481e2d9a595ee3bab4d3219247ac94e9a/pandas-3.0.2.tar.gz", hash = "sha256:f4753e73e34c8d83221ba58f232433fca2748be8b18dbca02d242ed153945043", size = 4645855, upload-time = "2026-03-31T06:48:30.816Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/f8/87/4341c6252d1c47b08768c3d25ac487362bf403f0313ddae4a2a26c9b1b4c/pandas-3.0.3.tar.gz", hash = "sha256:696a4a00a2a2a35d4e5deb3fc946641b96c944f02230e4f76137fe35d806c4fc", size = 4651414, upload-time = "2026-05-11T18:54:29.21Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/97/35/6411db530c618e0e0005187e35aa02ce60ae4c4c4d206964a2f978217c27/pandas-3.0.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a727a73cbdba2f7458dc82449e2315899d5140b449015d822f515749a46cbbe0", size = 10326926, upload-time = "2026-03-31T06:46:08.29Z" },
-    { url = "https://files.pythonhosted.org/packages/c4/d3/b7da1d5d7dbdc5ef52ed7debd2b484313b832982266905315dad5a0bf0b1/pandas-3.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:dbbd4aa20ca51e63b53bbde6a0fa4254b1aaabb74d2f542df7a7959feb1d760c", size = 9926987, upload-time = "2026-03-31T06:46:11.724Z" },
-    { url = "https://files.pythonhosted.org/packages/52/77/9b1c2d6070b5dbe239a7bc889e21bfa58720793fb902d1e070695d87c6d0/pandas-3.0.2-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:339dda302bd8369dedeae979cb750e484d549b563c3f54f3922cb8ff4978c5eb", size = 10757067, upload-time = "2026-03-31T06:46:14.903Z" },
-    { url = "https://files.pythonhosted.org/packages/20/17/ec40d981705654853726e7ac9aea9ddbb4a5d9cf54d8472222f4f3de06c2/pandas-3.0.2-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:61c2fd96d72b983a9891b2598f286befd4ad262161a609c92dc1652544b46b76", size = 11258787, upload-time = "2026-03-31T06:46:17.683Z" },
-    { url = "https://files.pythonhosted.org/packages/90/e3/3f1126d43d3702ca8773871a81c9f15122a1f412342cc56284ffda5b1f70/pandas-3.0.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c934008c733b8bbea273ea308b73b3156f0181e5b72960790b09c18a2794fe1e", size = 11771616, upload-time = "2026-03-31T06:46:20.532Z" },
-    { url = "https://files.pythonhosted.org/packages/2e/cf/0f4e268e1f5062e44a6bda9f925806721cd4c95c2b808a4c82ebe914f96b/pandas-3.0.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:60a80bb4feacbef5e1447a3f82c33209c8b7e07f28d805cfd1fb951e5cb443aa", size = 12337623, upload-time = "2026-03-31T06:46:23.754Z" },
-    { url = "https://files.pythonhosted.org/packages/44/a0/97a6339859d4acb2536efb24feb6708e82f7d33b2ed7e036f2983fcced82/pandas-3.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:ed72cb3f45190874eb579c64fa92d9df74e98fd63e2be7f62bce5ace0ade61df", size = 9897372, upload-time = "2026-03-31T06:46:26.703Z" },
-    { url = "https://files.pythonhosted.org/packages/8f/eb/781516b808a99ddf288143cec46b342b3016c3414d137da1fdc3290d8860/pandas-3.0.2-cp311-cp311-win_arm64.whl", hash = "sha256:f12b1a9e332c01e09510586f8ca9b108fd631fd656af82e452d7315ef6df5f9f", size = 9154922, upload-time = "2026-03-31T06:46:30.284Z" },
-    { url = "https://files.pythonhosted.org/packages/f3/b0/c20bd4d6d3f736e6bd6b55794e9cd0a617b858eaad27c8f410ea05d953b7/pandas-3.0.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:232a70ebb568c0c4d2db4584f338c1577d81e3af63292208d615907b698a0f18", size = 10347921, upload-time = "2026-03-31T06:46:33.36Z" },
-    { url = "https://files.pythonhosted.org/packages/35/d0/4831af68ce30cc2d03c697bea8450e3225a835ef497d0d70f31b8cdde965/pandas-3.0.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:970762605cff1ca0d3f71ed4f3a769ea8f85fc8e6348f6e110b8fea7e6eb5a14", size = 9888127, upload-time = "2026-03-31T06:46:36.253Z" },
-    { url = "https://files.pythonhosted.org/packages/61/a9/16ea9346e1fc4a96e2896242d9bc674764fb9049b0044c0132502f7a771e/pandas-3.0.2-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:aff4e6f4d722e0652707d7bcb190c445fe58428500c6d16005b02401764b1b3d", size = 10399577, upload-time = "2026-03-31T06:46:39.224Z" },
-    { url = "https://files.pythonhosted.org/packages/c4/a8/3a61a721472959ab0ce865ef05d10b0d6bfe27ce8801c99f33d4fa996e65/pandas-3.0.2-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ef8b27695c3d3dc78403c9a7d5e59a62d5464a7e1123b4e0042763f7104dc74f", size = 10880030, upload-time = "2026-03-31T06:46:42.412Z" },
-    { url = "https://files.pythonhosted.org/packages/da/65/7225c0ea4d6ce9cb2160a7fb7f39804871049f016e74782e5dade4d14109/pandas-3.0.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:f8d68083e49e16b84734eb1a4dcae4259a75c90fb6e2251ab9a00b61120c06ab", size = 11409468, upload-time = "2026-03-31T06:46:45.2Z" },
-    { url = "https://files.pythonhosted.org/packages/fa/5b/46e7c76032639f2132359b5cf4c785dd8cf9aea5ea64699eac752f02b9db/pandas-3.0.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:32cc41f310ebd4a296d93515fcac312216adfedb1894e879303987b8f1e2b97d", size = 11936381, upload-time = "2026-03-31T06:46:48.293Z" },
-    { url = "https://files.pythonhosted.org/packages/7b/8b/721a9cff6fa6a91b162eb51019c6243b82b3226c71bb6c8ef4a9bd65cbc6/pandas-3.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:a4785e1d6547d8427c5208b748ae2efb64659a21bd82bf440d4262d02bfa02a4", size = 9744993, upload-time = "2026-03-31T06:46:51.488Z" },
-    { url = "https://files.pythonhosted.org/packages/d5/18/7f0bd34ae27b28159aa80f2a6799f47fda34f7fb938a76e20c7b7fe3b200/pandas-3.0.2-cp312-cp312-win_arm64.whl", hash = "sha256:08504503f7101300107ecdc8df73658e4347586db5cfdadabc1592e9d7e7a0fd", size = 9056118, upload-time = "2026-03-31T06:46:54.548Z" },
-    { url = "https://files.pythonhosted.org/packages/bf/ca/3e639a1ea6fcd0617ca4e8ca45f62a74de33a56ae6cd552735470b22c8d3/pandas-3.0.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:b5918ba197c951dec132b0c5929a00c0bf05d5942f590d3c10a807f6e15a57d3", size = 10321105, upload-time = "2026-03-31T06:46:57.327Z" },
-    { url = "https://files.pythonhosted.org/packages/0b/77/dbc82ff2fb0e63c6564356682bf201edff0ba16c98630d21a1fb312a8182/pandas-3.0.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:d606a041c89c0a474a4702d532ab7e73a14fe35c8d427b972a625c8e46373668", size = 9864088, upload-time = "2026-03-31T06:46:59.935Z" },
-    { url = "https://files.pythonhosted.org/packages/5c/2b/341f1b04bbca2e17e13cd3f08c215b70ef2c60c5356ef1e8c6857449edc7/pandas-3.0.2-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:710246ba0616e86891b58ab95f2495143bb2bc83ab6b06747c74216f583a6ac9", size = 10369066, upload-time = "2026-03-31T06:47:02.792Z" },
-    { url = "https://files.pythonhosted.org/packages/12/c5/cbb1ffefb20a93d3f0e1fdcda699fb84976210d411b008f97f48bf6ce27e/pandas-3.0.2-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5d3cfe227c725b1f3dff4278b43d8c784656a42a9325b63af6b1492a8232209e", size = 10876780, upload-time = "2026-03-31T06:47:06.205Z" },
-    { url = "https://files.pythonhosted.org/packages/98/fe/2249ae5e0a69bd0ddf17353d0a5d26611d70970111f5b3600cdc8be883e7/pandas-3.0.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:c3b723df9087a9a9a840e263ebd9f88b64a12075d1bf2ea401a5a42f254f084d", size = 11375181, upload-time = "2026-03-31T06:47:09.383Z" },
-    { url = "https://files.pythonhosted.org/packages/de/64/77a38b09e70b6464883b8d7584ab543e748e42c1b5d337a2ee088e0df741/pandas-3.0.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:a3096110bf9eac0070b7208465f2740e2d8a670d5cb6530b5bb884eca495fd39", size = 11928899, upload-time = "2026-03-31T06:47:12.686Z" },
-    { url = "https://files.pythonhosted.org/packages/5e/52/42855bf626868413f761addd574acc6195880ae247a5346477a4361c3acb/pandas-3.0.2-cp313-cp313-win_amd64.whl", hash = "sha256:07a10f5c36512eead51bc578eb3354ad17578b22c013d89a796ab5eee90cd991", size = 9746574, upload-time = "2026-03-31T06:47:15.64Z" },
-    { url = "https://files.pythonhosted.org/packages/88/39/21304ae06a25e8bf9fc820d69b29b2c495b2ae580d1e143146c309941760/pandas-3.0.2-cp313-cp313-win_arm64.whl", hash = "sha256:5fdbfa05931071aba28b408e59226186b01eb5e92bea2ab78b65863ca3228d84", size = 9047156, upload-time = "2026-03-31T06:47:18.595Z" },
-    { url = "https://files.pythonhosted.org/packages/72/20/7defa8b27d4f330a903bb68eea33be07d839c5ea6bdda54174efcec0e1d2/pandas-3.0.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:dbc20dea3b9e27d0e66d74c42b2d0c1bed9c2ffe92adea33633e3bedeb5ac235", size = 10756238, upload-time = "2026-03-31T06:47:22.012Z" },
-    { url = "https://files.pythonhosted.org/packages/e9/95/49433c14862c636afc0e9b2db83ff16b3ad92959364e52b2955e44c8e94c/pandas-3.0.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:b75c347eff42497452116ce05ef461822d97ce5b9ff8df6edacb8076092c855d", size = 10408520, upload-time = "2026-03-31T06:47:25.197Z" },
-    { url = "https://files.pythonhosted.org/packages/3b/f8/462ad2b5881d6b8ec8e5f7ed2ea1893faa02290d13870a1600fe72ad8efc/pandas-3.0.2-cp313-cp313t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d1478075142e83a5571782ad007fb201ed074bdeac7ebcc8890c71442e96adf7", size = 10324154, upload-time = "2026-03-31T06:47:28.097Z" },
-    { url = "https://files.pythonhosted.org/packages/0a/65/d1e69b649cbcddda23ad6e4c40ef935340f6f652a006e5cbc3555ac8adb3/pandas-3.0.2-cp313-cp313t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5880314e69e763d4c8b27937090de570f1fb8d027059a7ada3f7f8e98bdcb677", size = 10714449, upload-time = "2026-03-31T06:47:30.85Z" },
-    { url = "https://files.pythonhosted.org/packages/47/a4/85b59bc65b8190ea3689882db6cdf32a5003c0ccd5a586c30fdcc3ffc4fc/pandas-3.0.2-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:b5329e26898896f06035241a626d7c335daa479b9bbc82be7c2742d048e41172", size = 11338475, upload-time = "2026-03-31T06:47:34.026Z" },
-    { url = "https://files.pythonhosted.org/packages/1e/c4/bc6966c6e38e5d9478b935272d124d80a589511ed1612a5d21d36f664c68/pandas-3.0.2-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:81526c4afd31971f8b62671442a4b2b51e0aa9acc3819c9f0f12a28b6fcf85f1", size = 11786568, upload-time = "2026-03-31T06:47:36.941Z" },
-    { url = "https://files.pythonhosted.org/packages/e8/74/09298ca9740beed1d3504e073d67e128aa07e5ca5ca2824b0c674c0b8676/pandas-3.0.2-cp313-cp313t-win_amd64.whl", hash = "sha256:7cadd7e9a44ec13b621aec60f9150e744cfc7a3dd32924a7e2f45edff31823b0", size = 10488652, upload-time = "2026-03-31T06:47:40.612Z" },
-    { url = "https://files.pythonhosted.org/packages/bb/40/c6ea527147c73b24fc15c891c3fcffe9c019793119c5742b8784a062c7db/pandas-3.0.2-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:db0dbfd2a6cdf3770aa60464d50333d8f3d9165b2f2671bcc299b72de5a6677b", size = 10326084, upload-time = "2026-03-31T06:47:43.834Z" },
-    { url = "https://files.pythonhosted.org/packages/95/25/bdb9326c3b5455f8d4d3549fce7abcf967259de146fe2cf7a82368141948/pandas-3.0.2-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:0555c5882688a39317179ab4a0ed41d3ebc8812ab14c69364bbee8fb7a3f6288", size = 9914146, upload-time = "2026-03-31T06:47:46.67Z" },
-    { url = "https://files.pythonhosted.org/packages/8d/77/3a227ff3337aa376c60d288e1d61c5d097131d0ac71f954d90a8f369e422/pandas-3.0.2-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:01f31a546acd5574ef77fe199bc90b55527c225c20ccda6601cf6b0fd5ed597c", size = 10444081, upload-time = "2026-03-31T06:47:49.681Z" },
-    { url = "https://files.pythonhosted.org/packages/15/88/3cdd54fa279341afa10acf8d2b503556b1375245dccc9315659f795dd2e9/pandas-3.0.2-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:deeca1b5a931fdf0c2212c8a659ade6d3b1edc21f0914ce71ef24456ca7a6535", size = 10897535, upload-time = "2026-03-31T06:47:53.033Z" },
-    { url = "https://files.pythonhosted.org/packages/06/9d/98cc7a7624f7932e40f434299260e2917b090a579d75937cb8a57b9d2de3/pandas-3.0.2-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:0f48afd9bb13300ffb5a3316973324c787054ba6665cda0da3fbd67f451995db", size = 11446992, upload-time = "2026-03-31T06:47:56.193Z" },
-    { url = "https://files.pythonhosted.org/packages/9a/cd/19ff605cc3760e80602e6826ddef2824d8e7050ed80f2e11c4b079741dc3/pandas-3.0.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:6c4d8458b97a35717b62469a4ea0e85abd5ed8687277f5ccfc67f8a5126f8c53", size = 11968257, upload-time = "2026-03-31T06:47:59.137Z" },
-    { url = "https://files.pythonhosted.org/packages/db/60/aba6a38de456e7341285102bede27514795c1eaa353bc0e7638b6b785356/pandas-3.0.2-cp314-cp314-win_amd64.whl", hash = "sha256:b35d14bb5d8285d9494fe93815a9e9307c0876e10f1e8e89ac5b88f728ec8dcf", size = 9865893, upload-time = "2026-03-31T06:48:02.038Z" },
-    { url = "https://files.pythonhosted.org/packages/08/71/e5ec979dd2e8a093dacb8864598c0ff59a0cee0bbcdc0bfec16a51684d4f/pandas-3.0.2-cp314-cp314-win_arm64.whl", hash = "sha256:63d141b56ef686f7f0d714cfb8de4e320475b86bf4b620aa0b7da89af8cbdbbb", size = 9188644, upload-time = "2026-03-31T06:48:05.045Z" },
-    { url = "https://files.pythonhosted.org/packages/f1/6c/7b45d85db19cae1eb524f2418ceaa9d85965dcf7b764ed151386b7c540f0/pandas-3.0.2-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:140f0cffb1fa2524e874dde5b477d9defe10780d8e9e220d259b2c0874c89d9d", size = 10776246, upload-time = "2026-03-31T06:48:07.789Z" },
-    { url = "https://files.pythonhosted.org/packages/a8/3e/7b00648b086c106e81766f25322b48aa8dfa95b55e621dbdf2fdd413a117/pandas-3.0.2-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:ae37e833ff4fed0ba352f6bdd8b73ba3ab3256a85e54edfd1ab51ae40cca0af8", size = 10424801, upload-time = "2026-03-31T06:48:10.897Z" },
-    { url = "https://files.pythonhosted.org/packages/da/6e/558dd09a71b53b4008e7fc8a98ec6d447e9bfb63cdaeea10e5eb9b2dabe8/pandas-3.0.2-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4d888a5c678a419a5bb41a2a93818e8ed9fd3172246555c0b37b7cc27027effd", size = 10345643, upload-time = "2026-03-31T06:48:13.7Z" },
-    { url = "https://files.pythonhosted.org/packages/be/e3/921c93b4d9a280409451dc8d07b062b503bbec0531d2627e73a756e99a82/pandas-3.0.2-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b444dc64c079e84df91baa8bf613d58405645461cabca929d9178f2cd392398d", size = 10743641, upload-time = "2026-03-31T06:48:16.659Z" },
-    { url = "https://files.pythonhosted.org/packages/56/ca/fd17286f24fa3b4d067965d8d5d7e14fe557dd4f979a0b068ac0deaf8228/pandas-3.0.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:4544c7a54920de8eeacaa1466a6b7268ecfbc9bc64ab4dbb89c6bbe94d5e0660", size = 11361993, upload-time = "2026-03-31T06:48:19.475Z" },
-    { url = "https://files.pythonhosted.org/packages/e4/a5/2f6ed612056819de445a433ca1f2821ac3dab7f150d569a59e9cc105de1d/pandas-3.0.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:734be7551687c00fbd760dc0522ed974f82ad230d4a10f54bf51b80d44a08702", size = 11815274, upload-time = "2026-03-31T06:48:22.695Z" },
-    { url = "https://files.pythonhosted.org/packages/00/2f/b622683e99ec3ce00b0854bac9e80868592c5b051733f2cf3a868e5fea26/pandas-3.0.2-cp314-cp314t-win_amd64.whl", hash = "sha256:57a07209bebcbcf768d2d13c9b78b852f9a15978dac41b9e6421a81ad4cdd276", size = 10888530, upload-time = "2026-03-31T06:48:25.806Z" },
-    { url = "https://files.pythonhosted.org/packages/cb/2b/f8434233fab2bd66a02ec014febe4e5adced20e2693e0e90a07d118ed30e/pandas-3.0.2-cp314-cp314t-win_arm64.whl", hash = "sha256:5371b72c2d4d415d08765f32d689217a43227484e81b2305b52076e328f6f482", size = 9455341, upload-time = "2026-03-31T06:48:28.418Z" },
+    { url = "https://files.pythonhosted.org/packages/42/16/b5c76b838fd9bf6ce84d3a53346b8874ec05c5f0040d75ef2c320100cd2a/pandas-3.0.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:455f6f8139d4282188f526868dbc3c828470e88a3d9d59a891bd46a455f21b98", size = 10338495, upload-time = "2026-05-11T18:52:11.558Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/b0/a4ffc4ae74d2d822200dcc46898987d8eb6032d1e2b219cae39da6f5cbcc/pandas-3.0.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4e15135e2ee5df1063313e2425ceef8ac0f4ae775893815b0923651b806a5639", size = 9938250, upload-time = "2026-05-11T18:52:17.005Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/b2/3323601a52caee42c019e370090ca4544b241437240ca04f786cce82b0cf/pandas-3.0.3-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:05f1f1752b8533ea03f7f39a9c15b1a058d067bb48f4748948e7a8691e0510f2", size = 10770558, upload-time = "2026-05-11T18:52:19.865Z" },
+    { url = "https://files.pythonhosted.org/packages/32/f1/bbecd2f867b97abebe0f9b53d750f862251b40337e061b36676ded3d920f/pandas-3.0.3-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8a1e45c80cceb3b4a21bc5939d52e8cbd8d9b7305309219d59e9754d9ce09e27", size = 11274611, upload-time = "2026-05-11T18:52:22.622Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/4f/eafabf2d5fae5adf143b4d18d3706c5efdc368a7c4eb1ee8a3eddabbd0f6/pandas-3.0.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:14da8316da4d0c5a77618425996bfb1248ca87fc2c1486e6fde4652bd18b5824", size = 11784670, upload-time = "2026-05-11T18:52:25.4Z" },
+    { url = "https://files.pythonhosted.org/packages/49/44/1eb20389301b57b19cc099a1c2f662501f72f08a65f912d05822613c1532/pandas-3.0.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:a55066a0505dae0ba2b50a46637db34b46f9094c65c5d4800794ef6335010938", size = 12353708, upload-time = "2026-05-11T18:52:28.139Z" },
+    { url = "https://files.pythonhosted.org/packages/eb/62/c321f13b5ba1819fc8dca456c7fce578da2dcfecff1abbf0eaddf8406c0f/pandas-3.0.3-cp311-cp311-win_amd64.whl", hash = "sha256:6674ab18ad8c57802867264b00e15e7bb904700cdd9046e3b2fa1fce237439ea", size = 9907609, upload-time = "2026-05-11T18:52:30.982Z" },
+    { url = "https://files.pythonhosted.org/packages/53/85/1b7f563ebc6357c27233a02a96b589bcce1fa9c6eb89fb4f0e56421d277e/pandas-3.0.3-cp311-cp311-win_arm64.whl", hash = "sha256:5cc09a68b3120e0f54870dede8287a7bb1fa463907e4fcec1ea77cab6179bf7a", size = 9165596, upload-time = "2026-05-11T18:52:33.334Z" },
+    { url = "https://files.pythonhosted.org/packages/24/f1/392f8c5bfc16f66a0d2d41561c01627c228fe7ed2a0d056ef11315042570/pandas-3.0.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:fed2ff7fd9779120e388e285fc029bd5cf9490cdd2e4166a9ee22c0e49a9ab09", size = 10357846, upload-time = "2026-05-11T18:52:36.143Z" },
+    { url = "https://files.pythonhosted.org/packages/cf/3d/b16412745651e855f357e5e66930248688378853a6e2698a214e331fba1f/pandas-3.0.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b168fc218fd80a6cbdbdbc1a97ddc7889ed057d7eb45f50d866ceab5f39904c4", size = 9899550, upload-time = "2026-05-11T18:52:38.976Z" },
+    { url = "https://files.pythonhosted.org/packages/31/a8/fa2535168fffcedf67f4f6de28d2dd903a747ca7c8ea6989451aaeb3a92f/pandas-3.0.3-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0383c72c75cdcca61a9e116e611143902dbfd08bff356829c2f6d1cf40a9ca8c", size = 10412965, upload-time = "2026-05-11T18:52:41.915Z" },
+    { url = "https://files.pythonhosted.org/packages/65/b6/09b01cdbc15224e2850365192d17b7bdebb8bdbd8780ed221fcdf0d9a515/pandas-3.0.3-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6dc0b3fd2169c9157deed50b4d519553a3655c8c6a96027136d654592be973a9", size = 10894600, upload-time = "2026-05-11T18:52:45.02Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/a4/2eb28f2fccb4ced4a2c79ab2a5dee9ade1ebf44922ebad6fea158c9f95d4/pandas-3.0.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:7e65d5407dc0b394f509699650e4a2ec01c0514f21850f453fa60f3be79a5dbf", size = 11422824, upload-time = "2026-05-11T18:52:48.058Z" },
+    { url = "https://files.pythonhosted.org/packages/f8/45/830bb57f533a4604b355e07edcb8ea18cf88b5f94e5fca92f27052d7c597/pandas-3.0.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:f8894dc474d648fe7b6ff0ca9b0bd73950d19952bc1a6534540762c5d79d305c", size = 11950889, upload-time = "2026-05-11T18:52:50.905Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/c5/fc1b368f303087d20e8c9bf3d6ceb186263cfac0ade735cd938538bea839/pandas-3.0.3-cp312-cp312-win_amd64.whl", hash = "sha256:c7be265b62cef88e253a941e4698604973736dcfe242fdb5198f0f7bc473cdcc", size = 9755463, upload-time = "2026-05-11T18:52:53.386Z" },
+    { url = "https://files.pythonhosted.org/packages/86/bd/fda8f9705b1b09c6ebe14bfc0fa0e4ec8584d54ea673628f157ff55131af/pandas-3.0.3-cp312-cp312-win_arm64.whl", hash = "sha256:557409bc4178e70ee8d9ddb494798e51ebf6ea59330f6be22c51bab2a7db6c49", size = 9066158, upload-time = "2026-05-11T18:52:56.038Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/90/62d8302883c44308c477e222c3daf7c813a34c8e96985882fbd53d964352/pandas-3.0.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:67b3b64c11910cfa29f4e94a14d3bff9ee693b6fc76055e7cad549cee0aec5fa", size = 10331071, upload-time = "2026-05-11T18:52:58.838Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/ae/6a6493c783a101f165e4356953ba3c74d6f77f0042fa7d753da9dfbb640c/pandas-3.0.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:39436b377d56d2a2e52d0395bdbee171f01068e99af5250509aceeb929f765c7", size = 9875690, upload-time = "2026-05-11T18:53:01.431Z" },
+    { url = "https://files.pythonhosted.org/packages/62/7c/5df8e9f56c69a2769fbe9382a5ef8f2658c007e376434e1e2cbb57ad895f/pandas-3.0.3-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d4be06d68f9ddcfc645b87534911da79a8fbffc7573c80e0edcf42a5020624d8", size = 10381634, upload-time = "2026-05-11T18:53:04.393Z" },
+    { url = "https://files.pythonhosted.org/packages/99/68/1237369725aa617bb358263d535803e3053fdbc593513ec5ed9c9896b5b6/pandas-3.0.3-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a4eeb6830daf35a71cc09649bd823e2b542dac246cdee9614c6e4bd65028cd6a", size = 10891243, upload-time = "2026-05-11T18:53:07.643Z" },
+    { url = "https://files.pythonhosted.org/packages/25/93/77d108e8af7222b4a503ebde0e30215b1c2e4f8e53a526431890f22d5586/pandas-3.0.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:1928e07221f82db493cd4af1e23c1bfca524a19a4699887975bff68f49a72bfb", size = 11388659, upload-time = "2026-05-11T18:53:10.634Z" },
+    { url = "https://files.pythonhosted.org/packages/d0/bd/eff5b4399f332ac386c853f6cd2bd3fa2ca0061b9f36ecd9c4d7c4265649/pandas-3.0.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:51b1fe551acb77dac643c6fda86084d8d446c10fe64b06a9cc29c4cc8540e7f2", size = 11942880, upload-time = "2026-05-11T18:53:13.536Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/20/559ace4200982c3887d0b86bfd0d856a2143ef8ddab63cc07934951a964c/pandas-3.0.3-cp313-cp313-win_amd64.whl", hash = "sha256:a82d532a3351d435432cd913edbccaf8b8e01d4dd0e5ced5a8d2e8ecd94c7e44", size = 9757091, upload-time = "2026-05-11T18:53:16.306Z" },
+    { url = "https://files.pythonhosted.org/packages/3a/66/69055a09fe200f29f922a3eeec4804611900b95f52d932ece3393c3c0c19/pandas-3.0.3-cp313-cp313-win_arm64.whl", hash = "sha256:275c14e0fce14a2ec20eee474aecd305478ea3c1e6f6a9d8fe219a165542717e", size = 9057282, upload-time = "2026-05-11T18:53:18.768Z" },
+    { url = "https://files.pythonhosted.org/packages/57/0e/efe801b0e6811e8e650cd21b7f2608e30f08a7067e2bf6e8752b0d56ee3c/pandas-3.0.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:46997386d528eb40376ecd6b033cf4a8a1e5282580f68f43de875b78cba2199d", size = 10767016, upload-time = "2026-05-11T18:53:21.227Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/dc/eb55135a1d5f0f0519f28da1f609a206d2cad1f9c35c32d51e38dd7261ae/pandas-3.0.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:261e308dfb22448384b7580cf719d2f998fe2966c92893c3e77d14008af1f066", size = 10420210, upload-time = "2026-05-11T18:53:23.982Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/3e/b1d5d955ce33ffecb407465a60bc32769d74fcf68224b7ae67ae11d4dea4/pandas-3.0.3-cp313-cp313t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:dd1a5d1def6a46002e964510bdc67c368aa0951df5d1d9f8365336f5a1f490cd", size = 10336126, upload-time = "2026-05-11T18:53:26.731Z" },
+    { url = "https://files.pythonhosted.org/packages/f5/76/a01261711ab60a22d71b862f0de20e4c504bf80457270ad8cb42110f6abc/pandas-3.0.3-cp313-cp313t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d72828c20c6d6e83e1e22a6a3b47b326b71664112fa9705dcbccfd7a39b62085", size = 10728051, upload-time = "2026-05-11T18:53:29.125Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/21/ea191195e587b18cf682e97f433f81b2d0fbe341380e80a3e0d6e4403c8e/pandas-3.0.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:d26cbe1fcfc12e8fd900e2454163e466b2d3af84f7c75481df7683ffc073d870", size = 11350796, upload-time = "2026-05-11T18:53:32.056Z" },
+    { url = "https://files.pythonhosted.org/packages/64/69/f0eaaf54939f0e8c6768fd06be9af2cef9b36048b96dfb9e1b2c685a807e/pandas-3.0.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:3e91cec1879ada0624fc3dc9953c5cbd60208e59c0db28f540c5d6d47502422f", size = 11799741, upload-time = "2026-05-11T18:53:34.985Z" },
+    { url = "https://files.pythonhosted.org/packages/45/a4/865e0e510cae5fc2194de4db28be638952de942571ba9125934fd9c01d47/pandas-3.0.3-cp313-cp313t-win_amd64.whl", hash = "sha256:08d789b41f87e0905880e293cedf6197ce71fe67cc081358b1e148a491b9bd13", size = 10499958, upload-time = "2026-05-11T18:53:37.857Z" },
+    { url = "https://files.pythonhosted.org/packages/86/54/effdcc3c0ff7a08037889200e148ebe94c16c4f653be078c7b3675955df1/pandas-3.0.3-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:3650109c0f22879df8bd6179ab9ee3d7f1d1d4e7e0094a3f0032d9f51e2e64ac", size = 10336065, upload-time = "2026-05-11T18:53:41.099Z" },
+    { url = "https://files.pythonhosted.org/packages/68/10/bf2d6738d72748b961a3751ab89522d58c54efc36a8e1a12161216cd45cf/pandas-3.0.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:bab900348131a7db1f69a7309ef141fd5680f1487094193bcbbb61791573bf8f", size = 9926101, upload-time = "2026-05-11T18:53:43.515Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/e9/e35cf11c8a136e757b956f5f0efdcaa50aecde85ea055f1898dfc68262f3/pandas-3.0.3-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ba7e08b9ac1d54569cd1e256e3668975ed624d6826f7b68df0342b012007bddb", size = 10457553, upload-time = "2026-05-11T18:53:46.394Z" },
+    { url = "https://files.pythonhosted.org/packages/58/3b/1cdec6772bdbaf7b25dab360c59f03cadf05492dd724c6540af905389b07/pandas-3.0.3-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9d71c63ae4ebdbf70209742096f1fc46a83a0613c99d4b23766cced9ff8cd62a", size = 10914065, upload-time = "2026-05-11T18:53:49.134Z" },
+    { url = "https://files.pythonhosted.org/packages/c4/c2/1ef644445fcd72e3627bceec77e3560636f87ddce4ed841afe76b83b5bf9/pandas-3.0.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:e3a2ec42c98ffa2565a67e08e218d06d72576d758d90facb7c00805194d8f360", size = 11459188, upload-time = "2026-05-11T18:53:52.527Z" },
+    { url = "https://files.pythonhosted.org/packages/7e/49/4d8d4f42cbc9c4adc7a1870f269c02cbd6cd40d059622c06fb298addcbad/pandas-3.0.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:335f62418ed562cfc3c49e9e196375c28b729dcef8543abf4f9438e381bf3c76", size = 11982966, upload-time = "2026-05-11T18:53:55.043Z" },
+    { url = "https://files.pythonhosted.org/packages/38/55/792619469bab9882d8bbd5865d45a72f6478762d04a9af4bf0d08c503e95/pandas-3.0.3-cp314-cp314-win_amd64.whl", hash = "sha256:3c20a521bbb85902f79f7270c80a59e1b5452d96d170c034f207181870f97ac5", size = 9876755, upload-time = "2026-05-11T18:53:58.067Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/af/33c469653b0ba03b50c3a98192d4c07f0c75c66b263ceb097fce0ee97d31/pandas-3.0.3-cp314-cp314-win_arm64.whl", hash = "sha256:a2d2dff8a04f3917b55ab3910c32990f8ddf7eceba114947838cefa976a68977", size = 9198658, upload-time = "2026-05-11T18:54:00.733Z" },
+    { url = "https://files.pythonhosted.org/packages/a2/fa/b8c257bd76b8bd060c3a9151c1fca05e9b9c5e3af5d0f549c0356f6d143d/pandas-3.0.3-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:0d589105b3c14645af1738ff279b2995102d8f7a03b0a66dc8d95550eb513e04", size = 10787242, upload-time = "2026-05-11T18:54:03.564Z" },
+    { url = "https://files.pythonhosted.org/packages/54/eb/f19206ffb0bf1919002969aa448b4702c6594845156a6f8050674855aac3/pandas-3.0.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:13fc1e853d9e04743d11ba75a985ccbc2a317fe07d8af61e445a6fd24dacd6a6", size = 10436369, upload-time = "2026-05-11T18:54:06.311Z" },
+    { url = "https://files.pythonhosted.org/packages/fd/24/c7c39fb4fe22b71a0c2d78bf0c585c600092d85f94f086d2b3b2f6ca27e2/pandas-3.0.3-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:819959dab7bbd0049c15623fbac4e29a191b9528160a61fb1032242d8ced2d9c", size = 10358306, upload-time = "2026-05-11T18:54:09.085Z" },
+    { url = "https://files.pythonhosted.org/packages/16/ec/dd2a9eb7fa1204df88c0864164e35b228ac581062ac612ba0a67fd812e4c/pandas-3.0.3-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:60ae316d3fd75d1858d450d0db0103ea2be3e7d4a95ec2f064f7e2ae63f7b028", size = 10758394, upload-time = "2026-05-11T18:54:11.956Z" },
+    { url = "https://files.pythonhosted.org/packages/95/6e/00c61ea8e85b4f6d8d35e11852a1a4998fc7fafc91c6a602d1cc9c972d64/pandas-3.0.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:bd3a518890b400d32f9023722dc9a9a5c969f00b415419a3c06c043f09bb5d7d", size = 11375717, upload-time = "2026-05-11T18:54:14.539Z" },
+    { url = "https://files.pythonhosted.org/packages/31/89/8fc1c268969fac43688d65fd92e67df24bd128d53cb4d2eee534cd307399/pandas-3.0.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:9c39be2d709d01fa972a0cabc522389fceca4f3969332ba25a7d6c5802cf976a", size = 11828897, upload-time = "2026-05-11T18:54:17.146Z" },
+    { url = "https://files.pythonhosted.org/packages/56/3b/e7d20dea247a3e6dc0bd8a6953854afbedc03951def4e7371e05e7263e25/pandas-3.0.3-cp314-cp314t-win_amd64.whl", hash = "sha256:4db8c527972a821cf5286b40ccc57642a39bc62e62022b42f99f8a67fca8c3a1", size = 10900855, upload-time = "2026-05-11T18:54:19.72Z" },
+    { url = "https://files.pythonhosted.org/packages/0f/54/68a0978d1ef8502b8492099beaa6e7a0c1b32e3b5d4f677f5810cb08711c/pandas-3.0.3-cp314-cp314t-win_arm64.whl", hash = "sha256:b2c95f8bfc1ee412bf482605d7bfd30c12d1d26bd59fdd91efeef1d4718decb1", size = 9466464, upload-time = "2026-05-11T18:54:22.754Z" },
 ]
 
 [[package]]
 name = "parso"
-version = "0.8.6"
+version = "0.8.7"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/81/76/a1e769043c0c0c9fe391b702539d594731a4362334cdf4dc25d0c09761e7/parso-0.8.6.tar.gz", hash = "sha256:2b9a0332696df97d454fa67b81618fd69c35a7b90327cbe6ba5c92d2c68a7bfd", size = 401621, upload-time = "2026-02-09T15:45:24.425Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/30/4b/90c937815137d43ce71ba043cd3566221e9df6b9c805f24b5d138c9d40a7/parso-0.8.7.tar.gz", hash = "sha256:eaaac4c9fdd5e9e8852dc778d2d7405897ec510f2a298071453e5e3a07914bb1", size = 401824, upload-time = "2026-05-01T23:13:02.138Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b6/61/fae042894f4296ec49e3f193aff5d7c18440da9e48102c3315e1bc4519a7/parso-0.8.6-py2.py3-none-any.whl", hash = "sha256:2c549f800b70a5c4952197248825584cb00f033b29c692671d3bf08bf380baff", size = 106894, upload-time = "2026-02-09T15:45:21.391Z" },
+    { url = "https://files.pythonhosted.org/packages/99/5d/8268b644392ee874ee82a635cd0df1773de230bde356c38de28e298392cc/parso-0.8.7-py2.py3-none-any.whl", hash = "sha256:a8926eb2a1b915486941fdbd31e86a4baf88fe8c210f25f2f35ecec5b574ca1c", size = 107025, upload-time = "2026-05-01T23:12:58.867Z" },
 ]
 
 [[package]]
@@ -1423,6 +1490,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/2a/2d/d4bf65e47cea8ff2c794a600c4fd1273a7902f268757c531e0ee9f18aa58/pooch-1.9.0-py3-none-any.whl", hash = "sha256:f265597baa9f760d25ceb29d0beb8186c243d6607b0f60b83ecf14078dbc703b", size = 67175, upload-time = "2026-01-30T19:15:08.36Z" },
 ]
 
+[[package]]
+name = "primepy"
+version = "1.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/35/77/0cfa1b4697cfb5336f3a96e8bc73327f64610be3a64c97275f1801afb395/primePy-1.3.tar.gz", hash = "sha256:25fd7e25344b0789a5984c75d89f054fcf1f180bef20c998e4befbac92de4669", size = 3914, upload-time = "2018-05-29T17:18:18.683Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/74/c1/bb7e334135859c3a92ec399bc89293ea73f28e815e35b43929c8db6af030/primePy-1.3-py3-none-any.whl", hash = "sha256:5ed443718765be9bf7e2ff4c56cdff71b42140a15b39d054f9d99f0009e2317a", size = 4040, upload-time = "2018-05-29T17:18:17.53Z" },
+]
+
 [[package]]
 name = "prompt-toolkit"
 version = "3.0.52"
@@ -1505,6 +1581,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/0c/c3/44f3fbbfa403ea2a7c779186dc20772604442dde72947e7d01069cbe98e3/pycparser-3.0-py3-none-any.whl", hash = "sha256:b727414169a36b7d524c1c3e31839a521725078d7b2ff038656844266160a992", size = 48172, upload-time = "2026-01-21T14:26:50.693Z" },
 ]
 
+[[package]]
+name = "pydub"
+version = "0.25.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/fe/9a/e6bca0eed82db26562c73b5076539a4a08d3cffd19c3cc5913a3e61145fd/pydub-0.25.1.tar.gz", hash = "sha256:980a33ce9949cab2a569606b65674d748ecbca4f0796887fd6f46173a7b0d30f", size = 38326, upload-time = "2021-03-10T02:09:54.659Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a6/53/d78dc063216e62fc55f6b2eebb447f6a4b0a59f55c8406376f76bf959b08/pydub-0.25.1-py2.py3-none-any.whl", hash = "sha256:65617e33033874b59d87db603aa1ed450633288aefead953b30bded59cb599a6", size = 32327, upload-time = "2021-03-10T02:09:53.503Z" },
+]
+
 [[package]]
 name = "pygments"
 version = "2.20.0"
@@ -1550,7 +1635,7 @@ wheels = [
 
 [[package]]
 name = "requests"
-version = "2.33.1"
+version = "2.34.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "certifi" },
@@ -1558,9 +1643,9 @@ dependencies = [
     { name = "idna" },
     { name = "urllib3" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/5f/a4/98b9c7c6428a668bf7e42ebb7c79d576a1c3c1e3ae2d47e674b468388871/requests-2.33.1.tar.gz", hash = "sha256:18817f8c57c6263968bc123d237e3b8b08ac046f5456bd1e307ee8f4250d3517", size = 134120, upload-time = "2026-03-30T16:09:15.531Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/ac/c3/e2a2b89f2d3e2179abd6d00ebd70bff6273f37fb3e0cc209f48b39d00cbf/requests-2.34.2.tar.gz", hash = "sha256:f288924cae4e29463698d6d60bc6a4da69c89185ad1e0bcc4104f584e960b9ed", size = 142856, upload-time = "2026-05-14T19:25:27.735Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d7/8e/7540e8a2036f79a125c1d2ebadf69ed7901608859186c856fa0388ef4197/requests-2.33.1-py3-none-any.whl", hash = "sha256:4e6d1ef462f3626a1f0a0a9c42dd93c63bad33f9f1c1937509b8c5c8718ab56a", size = 64947, upload-time = "2026-03-30T16:09:13.83Z" },
+    { url = "https://files.pythonhosted.org/packages/a0/f4/c67b0b3f1b9245e8d266f0f112c500d50e5b4e83cb6f3b71b6528104182a/requests-2.34.2-py3-none-any.whl", hash = "sha256:2a0d60c172f83ac6ab31e4554906c0f3b3588d37b5cb939b1c061f4907e278e0", size = 73075, upload-time = "2026-05-14T19:25:26.443Z" },
 ]
 
 [[package]]
@@ -1693,6 +1778,20 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e1/e3/c164c88b2e5ce7b24d667b9bd83589cf4f3520d97cad01534cd3c4f55fdb/setuptools-81.0.0-py3-none-any.whl", hash = "sha256:fdd925d5c5d9f62e4b74b30d6dd7828ce236fd6ed998a08d81de62ce5a6310d6", size = 1062021, upload-time = "2026-02-06T21:10:37.175Z" },
 ]
 
+[[package]]
+name = "silero-vad"
+version = "6.2.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "packaging" },
+    { name = "torch" },
+    { name = "torchaudio" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/32/d3/e31f526482782764aa4f70e20fd4545cf2e4a81a60b6fb0f089f6d107991/silero_vad-6.2.1.tar.gz", hash = "sha256:b23062b0e39fad17b1266fc23c1e7b4290219dbe82ce08510889e32f681f4b3b", size = 28913811, upload-time = "2026-02-24T08:41:59.329Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0b/2b/48566f29a8b53d856ceb1994f209122749b3fda0a733a07e82047257de7a/silero_vad-6.2.1-py3-none-any.whl", hash = "sha256:09de93c4d874bb19c53e62a47dd38be5f163cedad2b5599583231f2a84ef79cb", size = 9146242, upload-time = "2026-02-24T08:41:56.955Z" },
+]
+
 [[package]]
 name = "six"
 version = "1.17.0"
@@ -1723,28 +1822,28 @@ wheels = [
 
 [[package]]
 name = "soxr"
-version = "1.0.0"
+version = "1.1.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "numpy" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/42/7e/f4b461944662ad75036df65277d6130f9411002bfb79e9df7dff40a31db9/soxr-1.0.0.tar.gz", hash = "sha256:e07ee6c1d659bc6957034f4800c60cb8b98de798823e34d2a2bba1caa85a4509", size = 171415, upload-time = "2025-09-07T13:22:21.317Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/ed/11/27cebce4a108f77afea7c80545115536b45e3f11ebfb914f638fdd9ba847/soxr-1.1.0.tar.gz", hash = "sha256:9f228ae21c78fa9359ca98d8a5e8e91f30639e438e574133dace62c5b5309e44", size = 173067, upload-time = "2026-05-03T00:15:18.214Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/65/ce/a3262bc8733d3a4ce5f660ed88c3d97f4b12658b0909e71334cba1721dcb/soxr-1.0.0-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:28e19d74a5ef45c0d7000f3c70ec1719e89077379df2a1215058914d9603d2d8", size = 206739, upload-time = "2025-09-07T13:21:54.572Z" },
-    { url = "https://files.pythonhosted.org/packages/64/dc/e8cbd100b652697cc9865dbed08832e7e135ff533f453eb6db9e6168d153/soxr-1.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f8dc69fc18884e53b72f6141fdf9d80997edbb4fec9dc2942edcb63abbe0d023", size = 165233, upload-time = "2025-09-07T13:21:55.887Z" },
-    { url = "https://files.pythonhosted.org/packages/75/12/4b49611c9ba5e9fe6f807d0a83352516808e8e573f8b4e712fc0c17f3363/soxr-1.0.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3f15450e6f65f22f02fcd4c5a9219c873b1e583a73e232805ff160c759a6b586", size = 208867, upload-time = "2025-09-07T13:21:57.076Z" },
-    { url = "https://files.pythonhosted.org/packages/cc/70/92146ab970a3ef8c43ac160035b1e52fde5417f89adb10572f7e788d9596/soxr-1.0.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1f73f57452f9df37b4de7a4052789fcbd474a5b28f38bba43278ae4b489d4384", size = 242633, upload-time = "2025-09-07T13:21:58.621Z" },
-    { url = "https://files.pythonhosted.org/packages/b5/a7/628479336206959463d08260bffed87905e7ba9e3bd83ca6b405a0736e94/soxr-1.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:9f417c3d69236051cf5a1a7bad7c4bff04eb3d8fcaa24ac1cb06e26c8d48d8dc", size = 173814, upload-time = "2025-09-07T13:21:59.798Z" },
-    { url = "https://files.pythonhosted.org/packages/c5/c7/f92b81f1a151c13afb114f57799b86da9330bec844ea5a0d3fe6a8732678/soxr-1.0.0-cp312-abi3-macosx_10_14_x86_64.whl", hash = "sha256:abecf4e39017f3fadb5e051637c272ae5778d838e5c3926a35db36a53e3a607f", size = 205508, upload-time = "2025-09-07T13:22:01.252Z" },
-    { url = "https://files.pythonhosted.org/packages/ff/1d/c945fea9d83ea1f2be9d116b3674dbaef26ed090374a77c394b31e3b083b/soxr-1.0.0-cp312-abi3-macosx_11_0_arm64.whl", hash = "sha256:e973d487ee46aa8023ca00a139db6e09af053a37a032fe22f9ff0cc2e19c94b4", size = 163568, upload-time = "2025-09-07T13:22:03.558Z" },
-    { url = "https://files.pythonhosted.org/packages/b5/80/10640970998a1d2199bef6c4d92205f36968cddaf3e4d0e9fe35ddd405bd/soxr-1.0.0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e8ce273cca101aff3d8c387db5a5a41001ba76ef1837883438d3c652507a9ccc", size = 204707, upload-time = "2025-09-07T13:22:05.125Z" },
-    { url = "https://files.pythonhosted.org/packages/b1/87/2726603c13c2126cb8ded9e57381b7377f4f0df6ba4408e1af5ddbfdc3dd/soxr-1.0.0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e8f2a69686f2856d37823bbb7b78c3d44904f311fe70ba49b893af11d6b6047b", size = 238032, upload-time = "2025-09-07T13:22:06.428Z" },
-    { url = "https://files.pythonhosted.org/packages/ce/04/530252227f4d0721a5524a936336485dfb429bb206a66baf8e470384f4a2/soxr-1.0.0-cp312-abi3-win_amd64.whl", hash = "sha256:2a3b77b115ae7c478eecdbd060ed4f61beda542dfb70639177ac263aceda42a2", size = 172070, upload-time = "2025-09-07T13:22:07.62Z" },
-    { url = "https://files.pythonhosted.org/packages/99/77/d3b3c25b4f1b1aa4a73f669355edcaee7a52179d0c50407697200a0e55b9/soxr-1.0.0-cp314-cp314t-macosx_10_14_x86_64.whl", hash = "sha256:392a5c70c04eb939c9c176bd6f654dec9a0eaa9ba33d8f1024ed63cf68cdba0a", size = 209509, upload-time = "2025-09-07T13:22:08.773Z" },
-    { url = "https://files.pythonhosted.org/packages/8a/ee/3ca73e18781bb2aff92b809f1c17c356dfb9a1870652004bd432e79afbfa/soxr-1.0.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:fdc41a1027ba46777186f26a8fba7893be913383414135577522da2fcc684490", size = 167690, upload-time = "2025-09-07T13:22:10.259Z" },
-    { url = "https://files.pythonhosted.org/packages/bd/f0/eea8b5f587a2531657dc5081d2543a5a845f271a3bea1c0fdee5cebde021/soxr-1.0.0-cp314-cp314t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:449acd1dfaf10f0ce6dfd75c7e2ef984890df94008765a6742dafb42061c1a24", size = 209541, upload-time = "2025-09-07T13:22:11.739Z" },
-    { url = "https://files.pythonhosted.org/packages/64/59/2430a48c705565eb09e78346950b586f253a11bd5313426ced3ecd9b0feb/soxr-1.0.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:38b35c99e408b8f440c9376a5e1dd48014857cd977c117bdaa4304865ae0edd0", size = 243025, upload-time = "2025-09-07T13:22:12.877Z" },
-    { url = "https://files.pythonhosted.org/packages/3c/1b/f84a2570a74094e921bbad5450b2a22a85d58585916e131d9b98029c3e69/soxr-1.0.0-cp314-cp314t-win_amd64.whl", hash = "sha256:a39b519acca2364aa726b24a6fd55acf29e4c8909102e0b858c23013c38328e5", size = 184850, upload-time = "2025-09-07T13:22:14.068Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/49/3e6bc84f87439f222f40b616e9a29a170f41fb564710ea510df19dc26907/soxr-1.1.0-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:34cc92208c3c412c046813e69da639c04a792c6a41fbfd7d909d359cd3e97a2d", size = 205699, upload-time = "2026-05-03T00:14:46.67Z" },
+    { url = "https://files.pythonhosted.org/packages/2f/94/216f46096a85b07d1e6ba7fd44491402e912a3d688cd4f36f0a600ca155f/soxr-1.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:bd30f7201eac896ebf5db7b09156e6f1a1b82601900d29d9c8449bdad8365b11", size = 167381, upload-time = "2026-05-03T00:14:48.012Z" },
+    { url = "https://files.pythonhosted.org/packages/94/cb/06caa463b8181ec1981bd6376d4a873748b7008193188b8cfb60391eb131/soxr-1.1.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1577865e993f98ffb261257c3060fa76ec3db44ed3f181b16464268000424464", size = 210938, upload-time = "2026-05-03T00:14:49.768Z" },
+    { url = "https://files.pythonhosted.org/packages/86/47/d5964551ca818b7f0c7ef7f3899056263b60ef098a801066350a9672ca8f/soxr-1.1.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3da87e3ffa3e41823d873b051c7ecb2acebd8d1b6b46b752f5facf10a0d84ab9", size = 245268, upload-time = "2026-05-03T00:14:51.422Z" },
+    { url = "https://files.pythonhosted.org/packages/8f/29/371467eb86c7ba6810df0bfe9409bcd9c52ec5615b111190fafe23e4d2e1/soxr-1.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:ae30c48ac795378cf23ba3c7c640b8ff794af714ac388b9fd6b31a40b39e6e86", size = 176779, upload-time = "2026-05-03T00:14:53.09Z" },
+    { url = "https://files.pythonhosted.org/packages/06/8a/f3da7973b5f1b05d2d7e94d5376b881dcbc05297900cae6c3d33d95b209b/soxr-1.1.0-cp312-abi3-macosx_10_14_x86_64.whl", hash = "sha256:e0e09fa633ce2e67df08b298afced4d184f6e753fc330f241022250f1d0d61da", size = 204124, upload-time = "2026-05-03T00:14:54.505Z" },
+    { url = "https://files.pythonhosted.org/packages/03/dc/200013a74641f8774664bbcd2346c695c05c2e300ea792adcb40a293eed0/soxr-1.1.0-cp312-abi3-macosx_11_0_arm64.whl", hash = "sha256:d6a7ad82b8d5f3fcc04b1d2ca055562b96af571e1d4fa7c6c61d0fb509ac43b4", size = 165457, upload-time = "2026-05-03T00:14:56.007Z" },
+    { url = "https://files.pythonhosted.org/packages/88/2b/2e5eba817a762a2ec589ff165b8bc5955b25a0ad140045f7cd8e45410543/soxr-1.1.0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:bf98c0d7b7d5ef5bf072fee8d3020e8b664f2d195933ea7bc5089267c2e22a06", size = 206529, upload-time = "2026-05-03T00:14:57.646Z" },
+    { url = "https://files.pythonhosted.org/packages/5c/f1/0e55195893228609c9a08c3b13b7a83a46c3a992cd00d3304f0f320cfb07/soxr-1.1.0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3b033078e86f3c4a658e5697fac8995764fad9e799563616b630136b613167f1", size = 240413, upload-time = "2026-05-03T00:14:59.363Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/4d/621e4150e4815246ad552d215a8a294a90143fedd19ee442cf82d3b3abc8/soxr-1.1.0-cp312-abi3-win_amd64.whl", hash = "sha256:6ae2a174bffea94e8ead857dad85999d3f49f091774dbad5b046c0417d7092f4", size = 174357, upload-time = "2026-05-03T00:15:00.724Z" },
+    { url = "https://files.pythonhosted.org/packages/76/cd/77b74f1e95af0e11e52e9a034421aece7f7b45afd15a909afd41d5a5d102/soxr-1.1.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:a941f5aaa0b8abced24318105c1ea22576afcc1138c19f625716ce4e2f76ad64", size = 207990, upload-time = "2026-05-03T00:15:02.1Z" },
+    { url = "https://files.pythonhosted.org/packages/30/86/600cc31f982288167a59972746f117790162012546f995a32b5a55394b16/soxr-1.1.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:feebcba99ac99adb8009d46c8f4c1956b8c167576b0ae8a6fb47502e9a6f78e7", size = 169288, upload-time = "2026-05-03T00:15:03.75Z" },
+    { url = "https://files.pythonhosted.org/packages/39/e4/80cd9aae0645513db1076d4384e8b2d895faf5009218b4a04348012c54fc/soxr-1.1.0-cp314-cp314t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:52c9ca84e3dc656d83acc424574770e20ea8e0704dc3842d4e27b0fe9d3ba449", size = 211405, upload-time = "2026-05-03T00:15:05.395Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/d6/cc3c80ac9b2289da4cf46c5d53b05e4327e6f5560a25868d06f9e2213af1/soxr-1.1.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f4977323ef9c3aa3c2a26ff5fe0191c84b8fd759daf7afb1f25a91a55ad8b730", size = 244617, upload-time = "2026-05-03T00:15:07.134Z" },
+    { url = "https://files.pythonhosted.org/packages/d3/9e/f7af5fae841ffe32ed8440234ea2ad6adecca3bd92b6101076268c429000/soxr-1.1.0-cp314-cp314t-win_amd64.whl", hash = "sha256:e17d4ef9b0185214b2c0935605ae63f827ea423bc74964be44763d68d2b6c21e", size = 187253, upload-time = "2026-05-03T00:15:08.813Z" },
 ]
 
 [[package]]
@@ -1795,45 +1894,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/34/ae/e3707f6c1bc6f7aa0df600ba8075bfb8a19252140cd595335be60e25f9ee/standard_sunau-3.13.0-py3-none-any.whl", hash = "sha256:53af624a9529c41062f4c2fd33837f297f3baa196b0cfceffea6555654602622", size = 7364, upload-time = "2024-10-30T16:01:28.003Z" },
 ]
 
-[[package]]
-name = "study-asr"
-version = "0.1.0"
-source = { virtual = "." }
-dependencies = [
-    { name = "ipython" },
-    { name = "librosa" },
-    { name = "matplotlib" },
-    { name = "numpy" },
-    { name = "pandas" },
-    { name = "pillow" },
-    { name = "pyrubberband" },
-    { name = "setuptools" },
-    { name = "tensorboard" },
-    { name = "tensorboardx" },
-    { name = "torch" },
-    { name = "torchaudio" },
-    { name = "torchcodec" },
-    { name = "tqdm" },
-]
-
-[package.metadata]
-requires-dist = [
-    { name = "ipython", specifier = ">=9.10.1" },
-    { name = "librosa", specifier = ">=0.11.0" },
-    { name = "matplotlib", specifier = ">=3.10.8" },
-    { name = "numpy", specifier = ">=2.4.4" },
-    { name = "pandas", specifier = ">=3.0.2" },
-    { name = "pillow", specifier = ">=12.2.0" },
-    { name = "pyrubberband", specifier = ">=0.4.0" },
-    { name = "setuptools", specifier = "<82" },
-    { name = "tensorboard", specifier = ">=2.20.0" },
-    { name = "tensorboardx", specifier = ">=2.6.5" },
-    { name = "torch", specifier = "==2.8.0" },
-    { name = "torchaudio", specifier = "==2.8.0" },
-    { name = "torchcodec", specifier = "==0.7.0" },
-    { name = "tqdm", specifier = ">=4.67.3" },
-]
-
 [[package]]
 name = "sympy"
 version = "1.14.0"
@@ -1946,6 +2006,36 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/04/6e/650bb7f28f771af0cb791b02348db8b7f5f64f40f6829ee82aa6ce99aabe/torch-2.8.0-cp313-none-macosx_11_0_arm64.whl", hash = "sha256:7b677e17f5a3e69fdef7eb3b9da72622f8d322692930297e4ccb52fefc6c8211", size = 73632395, upload-time = "2025-08-06T14:55:28.645Z" },
 ]
 
+[[package]]
+name = "torch-audiomentations"
+version = "0.12.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "julius" },
+    { name = "torch" },
+    { name = "torch-pitch-shift" },
+    { name = "torchaudio" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/31/8d/2f8fd7e34c75f5ee8de4310c3bd3f22270acd44d1f809e2fe7c12fbf35f8/torch_audiomentations-0.12.0.tar.gz", hash = "sha256:b02d4c5eb86376986a53eb405cca5e34f370ea9284411237508e720c529f7888", size = 52094, upload-time = "2025-01-15T09:07:01.071Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/21/9d/1ee04f49c15d2d632f6f7102061d7c07652858e6d91b58a091531034e84f/torch_audiomentations-0.12.0-py3-none-any.whl", hash = "sha256:1b80b91d2016ccf83979622cac8f702072a79b7dcc4c2bee40f00b26433a786b", size = 48506, upload-time = "2025-01-15T09:06:59.687Z" },
+]
+
+[[package]]
+name = "torch-pitch-shift"
+version = "1.2.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "packaging" },
+    { name = "primepy" },
+    { name = "torch" },
+    { name = "torchaudio" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/79/a6/722a832bca75d5079f6731e005b3d0c2eec7c6c6863d030620952d143d57/torch_pitch_shift-1.2.5.tar.gz", hash = "sha256:6e1c7531f08d0f407a4c55e5ff8385a41355c5c5d27ab7fa08632e51defbd0ed", size = 4725, upload-time = "2024-09-25T19:10:12.922Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/27/4c/96ac2a09efb56cc3c41fb3ce9b6f4d8c0604499f7481d4a13a7b03e21382/torch_pitch_shift-1.2.5-py3-none-any.whl", hash = "sha256:6f8500cbc13f1c98b11cde1805ce5084f82cdd195c285f34287541f168a7c6a7", size = 5005, upload-time = "2024-09-25T19:10:11.521Z" },
+]
+
 [[package]]
 name = "torchaudio"
 version = "2.8.0"
@@ -2002,11 +2092,11 @@ wheels = [
 
 [[package]]
 name = "traitlets"
-version = "5.14.3"
+version = "5.15.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/eb/79/72064e6a701c2183016abbbfedaba506d81e30e232a68c9f0d6f6fcd1574/traitlets-5.14.3.tar.gz", hash = "sha256:9ed0579d3502c94b4b3732ac120375cda96f923114522847de4b3bb98b96b6b7", size = 161621, upload-time = "2024-04-19T11:11:49.746Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/1b/22/40f55b26baeab80c2d7b3f1db0682f8954e4617fee7d90ce634022ef05c6/traitlets-5.15.0.tar.gz", hash = "sha256:4fead733f81cf1c4c938e06f8ca4633896833c9d89eff878159457f4d4392971", size = 163197, upload-time = "2026-05-06T08:05:58.016Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/00/c0/8f5d070730d7836adc9c9b6408dec68c6ced86b304a9b26a14df072a6e8c/traitlets-5.14.3-py3-none-any.whl", hash = "sha256:b74e89e397b1ed28cc831db7aea759ba6640cb3de13090ca145426688ff1ac4f", size = 85359, upload-time = "2024-04-19T11:11:46.763Z" },
+    { url = "https://files.pythonhosted.org/packages/da/98/a9937a969d018a23badfea0b381f66783649d48e0ea6c41923265c3cbeb3/traitlets-5.15.0-py3-none-any.whl", hash = "sha256:fb36a18867a6803deab09f3c5e0fa81bb7b26a5c9e82501c9933f759166eff40", size = 85877, upload-time = "2026-05-06T08:05:55.853Z" },
 ]
 
 [[package]]
@@ -2043,22 +2133,28 @@ wheels = [
 
 [[package]]
 name = "urllib3"
-version = "2.6.3"
+version = "2.7.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/c7/24/5f1b3bdffd70275f6661c76461e25f024d5a38a46f04aaca912426a2b1d3/urllib3-2.6.3.tar.gz", hash = "sha256:1b62b6884944a57dbe321509ab94fd4d3b307075e0c2eae991ac71ee15ad38ed", size = 435556, upload-time = "2026-01-07T16:24:43.925Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/53/0c/06f8b233b8fd13b9e5ee11424ef85419ba0d8ba0b3138bf360be2ff56953/urllib3-2.7.0.tar.gz", hash = "sha256:231e0ec3b63ceb14667c67be60f2f2c40a518cb38b03af60abc813da26505f4c", size = 433602, upload-time = "2026-05-07T16:13:18.596Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/39/08/aaaad47bc4e9dc8c725e68f9d04865dbcb2052843ff09c97b08904852d84/urllib3-2.6.3-py3-none-any.whl", hash = "sha256:bf272323e553dfb2e87d9bfd225ca7b0f467b919d7bbd355436d3fd37cb0acd4", size = 131584, upload-time = "2026-01-07T16:24:42.685Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/3e/5db95bcf282c52709639744ca2a8b149baccf648e39c8cc87553df9eae0c/urllib3-2.7.0-py3-none-any.whl", hash = "sha256:9fb4c81ebbb1ce9531cce37674bbc6f1360472bc18ca9a553ede278ef7276897", size = 131087, upload-time = "2026-05-07T16:13:17.151Z" },
 ]
 
 [[package]]
 name = "wcwidth"
-version = "0.6.0"
+version = "0.7.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/35/a2/8e3becb46433538a38726c948d3399905a4c7cabd0df578ede5dc51f0ec2/wcwidth-0.6.0.tar.gz", hash = "sha256:cdc4e4262d6ef9a1a57e018384cbeb1208d8abbc64176027e2c2455c81313159", size = 159684, upload-time = "2026-02-06T19:19:40.919Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/2c/ee/afaf0f85a9a18fe47a67f1e4422ed6cf1fe642f0ae0a2f81166231303c52/wcwidth-0.7.0.tar.gz", hash = "sha256:90e3a7ea092341c44b99562e75d09e4d5160fe7a3974c6fb842a101a95e7eed0", size = 182132, upload-time = "2026-05-02T16:04:12.653Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/68/5a/199c59e0a824a3db2b89c5d2dade7ab5f9624dbf6448dc291b46d5ec94d3/wcwidth-0.6.0-py3-none-any.whl", hash = "sha256:1a3a1e510b553315f8e146c54764f4fb6264ffad731b3d78088cdb1478ffbdad", size = 94189, upload-time = "2026-02-06T19:19:39.646Z" },
+    { url = "https://files.pythonhosted.org/packages/41/52/e465037f5375f43533d1a80b6923955201596a99142ed524d77b571a1418/wcwidth-0.7.0-py3-none-any.whl", hash = "sha256:5d69154c429a82910e241c738cd0e2976fac8a2dd47a1a805f4afed1c0f136f2", size = 110825, upload-time = "2026-05-02T16:04:11.033Z" },
 ]
 
+[[package]]
+name = "webrtcvad"
+version = "2.0.10"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/89/34/e2de2d97f3288512b9ea56f92e7452f8207eb5a0096500badf9dfd48f5e6/webrtcvad-2.0.10.tar.gz", hash = "sha256:f1bed2fb25b63fb7b1a55d64090c993c9c9167b28485ae0bcdd81cf6ede96aea", size = 66156, upload-time = "2017-01-07T23:05:18.732Z" }
+
 [[package]]
 name = "werkzeug"
 version = "3.1.8"