neverlib 0.2.6__py3-none-any.whl → 0.2.8__py3-none-any.whl

neverlib/utils/lazy_expose.py

@@ -0,0 +1,29 @@
+from lazy_loader import attach
+import importlib
+
+
+def attach_and_expose_all(pkg_name: str, g: dict, submodules, submod_attrs=None):
+    submod_attrs = submod_attrs or {}
+    _getattr, _dir, _all = attach(pkg_name, submodules=submodules, submod_attrs=submod_attrs)
+    _all_set = set(_all)
+
+    def __getattr__(name: str):
+        try:
+            return _getattr(name)
+        except AttributeError:
+            for mod in submodules:
+                m = importlib.import_module(f"{pkg_name}.{mod}")
+                if hasattr(m, name) and not name.startswith("_"):
+                    obj = getattr(m, name)
+                    g[name] = obj
+                    _all_set.add(name)
+                    return obj
+            raise
+
+    def __dir__():
+        # 避免为补全而导入所有子模块，保持冷启动轻量
+        # 仅返回 attach 提供的名称 + 已经懒暴露过的名称
+        return sorted(set(_dir()) | _all_set)
+
+    g["__all__"] = sorted(_all_set)
+    return __getattr__, __dir__, g["__all__"]

neverlib/utils/utils.py

@@ -12,6 +12,7 @@ from tqdm import tqdm
 from datetime import datetime
 import soundfile as sf
 import numpy as np
+
 EPS = np.finfo(float).eps
 
 
@@ -28,7 +29,10 @@ def get_path_list(source_path, end="*.wav", shuffle=False):
     return wav_list
 
 
-def get_audio_segments(sentence_len, wav_path_list, sr=16000, insert_silence=None):
+def get_audio_segments(sentence_len,
+                       wav_path_list,
+                       sr=16000,
+                       insert_silence=None):
     """
     从音频列表中随机拼接指定长度音频
     Args:
@@ -102,7 +106,8 @@ def TrainValSplit(dataset_dir, train_dir, val_dir, percentage=0.9):
     total_wav_num = len(wav_path_list)
     # 计算训练集和验证集的分割点
     split_idx = int(total_wav_num * percentage)
-    train_path_list, val_path_list = wav_path_list[:split_idx], wav_path_list[split_idx:]
+    train_path_list, val_path_list = wav_path_list[:split_idx], wav_path_list[
+        split_idx:]
 
     for train_wavpath in tqdm(train_path_list, desc="Copying train wav"):
         target_path = train_wavpath.replace(dataset_dir, train_dir)
@@ -119,7 +124,11 @@ def TrainValSplit(dataset_dir, train_dir, val_dir, percentage=0.9):
     print("Done!")
 
 
-def TrainValTestSplit(dataset_dir, train_dir, val_dir, test_dir, percentage=[0.8, 0.1, 0.1]):
+def TrainValTestSplit(dataset_dir,
+                      train_dir,
+                      val_dir,
+                      test_dir,
+                      percentage=[0.8, 0.1, 0.1]):
     """ 分割数据集为训练集、验证集和测试集
     :param dataset_dir: 源数据集地址
     :param train_dir: 训练集地址
@@ -160,7 +169,9 @@ def TrainValTestSplit(dataset_dir, train_dir, val_dir, test_dir, percentage=[0.8
             os.makedirs(os.path.split(target_path)[0])
         shutil.copy(test_wavpath, target_path)
 
-    print(f"完成! 训练集: {len(train_path_list)}个文件, 验证集: {len(val_path_list)}个文件, 测试集: {len(test_path_list)}个文件")
+    print(
+        f"完成! 训练集: {len(train_path_list)}个文件, 验证集: {len(val_path_list)}个文件, 测试集: {len(test_path_list)}个文件"
+    )
 
 
 def get_leaf_folders(directory):
@@ -178,7 +189,10 @@ def del_empty_folders(path):
         return
 
     # 获取子文件夹
-    subfolders = [os.path.join(path, d) for d in os.listdir(path) if os.path.isdir(os.path.join(path, d))]
+    subfolders = [
+        os.path.join(path, d) for d in os.listdir(path)
+        if os.path.isdir(os.path.join(path, d))
+    ]
 
     # 递归处理子文件夹
     for subfolder in subfolders:
@@ -254,7 +268,8 @@ def DatasetSubfloderSplit(source_dir, split_dirs, percentage=None):
 
     # 复制文件夹
     split_names = ['train', 'val', 'test']
-    for folders, target_dir, split_name in zip(split_folder_lists, split_dirs, split_names[:len(split_dirs)]):
+    for folders, target_dir, split_name in zip(split_folder_lists, split_dirs,
+                                               split_names[:len(split_dirs)]):
         for folder in tqdm(folders, desc=f"Copying {split_name} folders"):
             target_folder = folder.replace(source_dir, target_dir)
             os.makedirs(os.path.dirname(target_folder), exist_ok=True)
@@ -262,7 +277,8 @@ def DatasetSubfloderSplit(source_dir, split_dirs, percentage=None):
 
     # 打印统计信息
     print(f"Total folders: {total_folder_num}")
-    for folders, split_name in zip(split_folder_lists, split_names[:len(split_dirs)]):
+    for folders, split_name in zip(split_folder_lists,
+                                   split_names[:len(split_dirs)]):
         print(f"{split_name.capitalize()} folders: {len(folders)}")
 
 
@@ -290,7 +306,11 @@ def wav2pcm(wav_path, pcm_path):
     data.tofile(pcm_path)
 
 
-def save_weight_histogram(model, save_dir, mode=["params", "buffers"], ignore_name=["scale", "bias"], bins=100):
+def save_weight_histogram(model,
+                          save_dir,
+                          mode=["params", "buffers"],
+                          ignore_name=["scale", "bias"],
+                          bins=100):
     """
     保存模型权重分布直方图
     Args:
@@ -322,11 +342,15 @@ def save_weight_histogram(model, save_dir, mode=["params", "buffers"], ignore_na
             plt.ylabel("count")
             plt.grid(alpha=0.5)
             # 在右上角添加统计信息
-            plt.text(1, 1, f"max: {param_max:.2f}\n \
+            plt.text(1,
+                     1,
+                     f"max: {param_max:.2f}\n \
                             min: {param_min:.2f}\n \
                             mean: {param_mean:.2f}\n \
                             std: {param_std:.2f}",
-                     ha='right', va='top', transform=plt.gca().transAxes)
+                     ha='right',
+                     va='top',
+                     transform=plt.gca().transAxes)
             plt.hist(param, bins=bins)
             plt.savefig(os.path.join(save_dir, "param", f"{name}.png"))
             plt.close()
@@ -349,11 +373,30 @@ def save_weight_histogram(model, save_dir, mode=["params", "buffers"], ignore_na
             plt.ylabel("count")
             plt.grid(alpha=0.5)
             # 在右上角添加统计信息
-            plt.text(1, 1, f"max: {buffer_max:.2f}\n \
+            plt.text(1,
+                     1,
+                     f"max: {buffer_max:.2f}\n \
                             min: {buffer_min:.2f}\n \
                             mean: {buffer_mean:.2f}\n \
                             std: {buffer_std:.2f}",
-                     ha='right', va='top', transform=plt.gca().transAxes)
+                     ha='right',
+                     va='top',
+                     transform=plt.gca().transAxes)
             plt.hist(buffer, bins=bins)
             plt.savefig(os.path.join(save_dir, "buffer", f"{name}.png"))
             plt.close()
+
+
+def read_pcm(file_path, channels=5, sample_rate=16000, sample_width=2):
+    # Read raw binary data from the PCM file
+    with open(file_path, 'rb') as f:
+        raw_data = f.read()
+
+    # Convert binary data to numpy array of the correct dtype
+    audio_data = np.frombuffer(raw_data, dtype=np.int16)
+
+    # Reshape the data into a 2D array with shape (num_frames, channels)
+    num_frames = len(audio_data) // channels
+    audio_data = audio_data.reshape((num_frames, channels))
+
+    return audio_data

neverlib/vad/PreProcess.py

@@ -1,66 +1,66 @@
-'''
-Author: 凌逆战 | Never
-Date: 2025-02-13 20:06:07
-LastEditTime: 2025-08-16 02:07:24
-FilePath: \neverlib\vad\PreProcess.py
-Description: 
-'''
-# -*- coding:utf-8 -*-
-# Author:凌逆战 | Never
-# Date: 2024/9/14
-"""
-通过一些预处理方法, 来提高VAD的准确率
-"""
-import numpy as np
-import noisereduce as nr
-
-
-def pre_emphasis(audio_data, alpha=0.97):
-    """
-    预加重
-    """
-    # y(n)=x(n)−α⋅x(n−1)
-    emphasized_audio = np.append(audio_data[0], audio_data[1:] - alpha * audio_data[:-1])
-    return emphasized_audio
-
-
-def NS(wav, sr=16000, stationary=True, prop_decrease=1.):
-    """ 传统降噪 Doc: https://pypi.org/project/noisereduce/
-    :param wav: (xxx,) or (channels, xxx)
-    :param sr: 采样率
-    :param stationary: 平稳降噪还是非平稳降噪
-    :param prop_decrease: 0~1, 降噪噪声百分比
-    :return:
-    """
-    if stationary:
-        # 平稳噪声抑制 stationary=True
-        reduced_noise = nr.reduce_noise(y=wav, sr=sr, stationary=True,
-                                        prop_decrease=prop_decrease,  # 降噪噪声的比例
-                                        )
-    else:
-        # 非平稳噪声抑制 stationary=False
-        reduced_noise = nr.reduce_noise(y=wav, sr=sr, stationary=False,
-                                        prop_decrease=prop_decrease,
-                                        )
-    return reduced_noise
-
-
-def NS_test():
-    import soundfile as sf
-    sr = 16000
-    wav_path = "../../data/vad_example.wav"
-    wav, wav_sr = sf.read(wav_path, always_2d=False, dtype="float32")
-    wav_NS = NS(wav, sr=sr, stationary=True, prop_decrease=0.6)
-    sf.write("../../wav_data/000_short_NS.wav", wav_NS, samplerate=sr)
-
-    # 绘制降噪后的频谱图
-    import matplotlib.pyplot as plt
-    plt.subplot(211)
-    plt.specgram(wav, Fs=sr, scale_by_freq=True, sides='default', cmap="jet")
-    plt.subplot(212)
-    plt.specgram(wav_NS, Fs=sr, scale_by_freq=True, sides='default', cmap="jet")
-    plt.show()
-
-
-if __name__ == "__main__":
-    NS_test()
+'''
+Author: 凌逆战 | Never
+Date: 2025-02-13 20:06:07
+LastEditTime: 2025-08-16 02:07:24
+FilePath: \\neverlib\\vad\\PreProcess.py
+Description: 
+'''
+# -*- coding:utf-8 -*-
+# Author:凌逆战 | Never
+# Date: 2024/9/14
+"""
+通过一些预处理方法, 来提高VAD的准确率
+"""
+import numpy as np
+import noisereduce as nr
+
+
+def pre_emphasis(audio_data, alpha=0.97):
+    """
+    预加重
+    """
+    # y(n)=x(n)−α⋅x(n−1)
+    emphasized_audio = np.append(audio_data[0], audio_data[1:] - alpha * audio_data[:-1])
+    return emphasized_audio
+
+
+def NS(wav, sr=16000, stationary=True, prop_decrease=1.):
+    """ 传统降噪 Doc: https://pypi.org/project/noisereduce/
+    :param wav: (xxx,) or (channels, xxx)
+    :param sr: 采样率
+    :param stationary: 平稳降噪还是非平稳降噪
+    :param prop_decrease: 0~1, 降噪噪声百分比
+    :return:
+    """
+    if stationary:
+        # 平稳噪声抑制 stationary=True
+        reduced_noise = nr.reduce_noise(y=wav, sr=sr, stationary=True,
+                                        prop_decrease=prop_decrease,  # 降噪噪声的比例
+                                        )
+    else:
+        # 非平稳噪声抑制 stationary=False
+        reduced_noise = nr.reduce_noise(y=wav, sr=sr, stationary=False,
+                                        prop_decrease=prop_decrease,
+                                        )
+    return reduced_noise
+
+
+def NS_test():
+    import soundfile as sf
+    sr = 16000
+    wav_path = "../../data/vad_example.wav"
+    wav, wav_sr = sf.read(wav_path, always_2d=False, dtype="float32")
+    wav_NS = NS(wav, sr=sr, stationary=True, prop_decrease=0.6)
+    sf.write("../../wav_data/000_short_NS.wav", wav_NS, samplerate=sr)
+
+    # 绘制降噪后的频谱图
+    import matplotlib.pyplot as plt
+    plt.subplot(211)
+    plt.specgram(wav, Fs=sr, scale_by_freq=True, sides='default', cmap="jet")
+    plt.subplot(212)
+    plt.specgram(wav_NS, Fs=sr, scale_by_freq=True, sides='default', cmap="jet")
+    plt.show()
+
+
+if __name__ == "__main__":
+    NS_test()

neverlib/vad/__init__.py

@@ -1,25 +1,71 @@
-# -*- coding:utf-8 -*-
-# Author:凌逆战 | Never
-# Date: 2024/5/17
-"""
-节省路径
-from neverlib.vad import EnergyVad_C
-如果没有用户必须完整路径
-from neverlib.vad.VAD_Energy import EnergyVad_C
-"""
-from lazy_loader import attach
-
-__getattr__, __dir__, __all__ = attach(
-    __name__,
-    submodules=["PreProcess", "VAD_Energy", "VAD_funasr", "VAD_Silero", "VAD_statistics", "VAD_vadlib", "VAD_WebRTC", "VAD_whisper", "utils"],
-    submod_attrs={
-        "VAD_Energy": ["EnergyVad_C"],
-        "VAD_funasr": ["FunASR_VAD_C"],
-        "VAD_Silero": ["Silero_VAD_C"],
-        "VAD_statistics": ["Statistics_VAD"],
-        "VAD_vadlib": ["Vadlib_C"],
-        "VAD_WebRTC": ["WebRTC_VAD_C"],
-        "VAD_whisper": ["Whisper_VAD_C"],
-        "utils": ["from_vadArray_to_vadEndpoint", "vad2nad"],
-    },
-)
+# This file is auto-generated. Do NOT edit manually.
+# Generated by neverlib.QA.gen_init
+
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    # 仅在类型检查时导入，提供IDE补全支持
+    from .PreProcess import NS, NS_test, pre_emphasis
+    from .VAD_Energy import EnergyVad_C
+    from .VAD_Silero import Silero_VAD_C
+    from .VAD_WebRTC import WebRTC_VAD_C
+    from .VAD_funasr import FunASR_VAD_C
+    from .VAD_statistics import Statistics_VAD
+    from .VAD_vadlib import Vadlib_C
+    from .VAD_whisper import Whisper_VAD_C
+    from .class_get_speech import getSpeech
+    from .class_vad import VADClass
+    from .utils import from_vadArray_to_vadEndpoint, vad2nad, vad_smooth
+
+# 运行时使用懒加载
+from lazy_loader import attach
+
+__getattr__, __dir__, __all__ = attach(
+    __name__,
+    submodules=[
+        "PreProcess",
+        "VAD_Energy",
+        "VAD_Silero",
+        "VAD_WebRTC",
+        "VAD_funasr",
+        "VAD_statistics",
+        "VAD_vadlib",
+        "VAD_whisper",
+        "class_get_speech",
+        "class_vad",
+        "utils",
+    ],
+    submod_attrs={
+        "PreProcess": ['NS', 'NS_test', 'pre_emphasis'],
+        "VAD_Energy": ['EnergyVad_C'],
+        "VAD_Silero": ['Silero_VAD_C'],
+        "VAD_WebRTC": ['WebRTC_VAD_C'],
+        "VAD_funasr": ['FunASR_VAD_C'],
+        "VAD_statistics": ['Statistics_VAD'],
+        "VAD_vadlib": ['Vadlib_C'],
+        "VAD_whisper": ['Whisper_VAD_C'],
+        "class_get_speech": ['getSpeech'],
+        "class_vad": ['VADClass'],
+        "utils": ['from_vadArray_to_vadEndpoint', 'vad2nad', 'vad_smooth'],
+    }
+)
+
+# 显式声明 __all__ 以便 IDE 识别
+if TYPE_CHECKING:
+    __all__ = [
+        'NS',
+        'NS_test',
+        'pre_emphasis',
+        'EnergyVad_C',
+        'Silero_VAD_C',
+        'WebRTC_VAD_C',
+        'FunASR_VAD_C',
+        'Statistics_VAD',
+        'Vadlib_C',
+        'Whisper_VAD_C',
+        'getSpeech',
+        'VADClass',
+        'from_vadArray_to_vadEndpoint',
+        'vad2nad',
+        'vad_smooth',
+    ]

neverlib/vad/class_get_speech.py

@@ -7,9 +7,9 @@
 import os
 import numpy as np
 import soundfile as sf
-from pydub.silence import split_on_silence
 from vad import EnergyVAD
 from pydub import AudioSegment
+from pydub.silence import split_on_silence
 
 
 class getSpeech():

neverlib/vad/class_vad.py

@@ -5,9 +5,8 @@
 一个包含众多VAD方法的类
 来源参考README
 """
-import numpy as np
-import soundfile as sf
 import torch
+import soundfile as sf
 
 
 class VADClass():
@@ -94,7 +93,8 @@ class VADClass():
         timestamps = []
         for chunk in result['chunks']:
             word_start, word_end = chunk['timestamp'][0], chunk['timestamp'][1]
-            if word_end == None: word_end = len(wav) / self.sr
+            if word_end == None:
+                word_end = len(wav) / self.sr
             timestamps.append({"start": int(word_start * self.sr), "end": int(word_end * self.sr)})
         return timestamps
 

{neverlib-0.2.6.dist-info → neverlib-0.2.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: neverlib
-Version: 0.2.6
+Version: 0.2.8
 Summary: A successful sign for python setup
 Author-email: "Never.Ling" <1786088386@qq.com>
 License: MIT

{neverlib-0.2.6.dist-info → neverlib-0.2.8.dist-info}/RECORD

@@ -1,4 +1,5 @@
-neverlib/__init__.py,sha256=zz5VnrI59Wl6wBRV5lbkViWeQHlR76cOJcPnzU9m1hc,945
+neverlib/__init__.py,sha256=Kq_ZWgw8gFiqQIN2gPzXkgti_zXUi2DYx0CD-88ExZU,2048
+neverlib/.claude/settings.local.json,sha256=nBol-eXbiZ3FMr1a7e6ls6CO9nwz5f3quPjEQzMkTyQ,126
 neverlib/.history/__init___20250805234212.py,sha256=RuVTeJiZfStZ12eMlEfTZ8ZjiC5RBaIQFht-bzMWdTs,1158
 neverlib/.history/__init___20250904102635.py,sha256=7G8jWnR8puUua7yvH63_AKM6rWGq0IvwgrincgrEs58,1081
 neverlib/.history/__init___20250904102836.py,sha256=R97n26izUmzFvB1K1e3Z4RA3-g0e6SBt_mI3YfsopO8,1002
@@ -399,55 +400,96 @@ neverlib/.specstory/history/2025-08-26_11-54Z-oserror-missing-shared-object-file
 neverlib/.specstory/history/2025-08-27_08-07Z-完善测试文档的讨论.md,sha256=1QlRvAsGRy11OvTjRbXj1Pd5ndaYku4gZL-yscFghZQ,9812
 neverlib/.specstory/history/2025-08-27_08-29Z-delete-python-file-command.md,sha256=rP1_LF0NhulirxWVgovUTOw7nu57LOg9ze4zMW-m21E,22061
 neverlib/.specstory/history/2025-08-27_09-05Z-在jupyter中播放音频的代码修改.md,sha256=87oxKHccYOlALgF9L7WW860Cjb_xjToCxDzAG4CXuQg,11587
+neverlib/Docs/audio_aug/test_volume.ipynb,sha256=K2qXRe8Md8rfiKsOhsGqAuEzxj2EPvAdRGaXDl0YrYY,18375
 neverlib/Docs/audio_aug_test/test_snr.py,sha256=1BRUzTYL37pblvhHNB0ORtrbNyxTFWytAxlJ8CDSwfM,1317
+neverlib/Docs/audio_aug_test/test_volume.ipynb,sha256=ZKDPm7Dr8ooZvO6nItshiVIY7jkh2a5AcmUw4wqsB0k,1843460
 neverlib/Docs/audio_aug_test/test_volume.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+neverlib/Docs/filter/biquad.ipynb,sha256=CRKHXUozpTaZXpdZSBRas3776SONAOUrWbkjYlMbvgY,3091
+neverlib/Docs/filter/filter_family.ipynb,sha256=EgXqDgP52KpdXkU_gPROb6ks5vZPzUVNf9Swrry0RRk,1135214
+neverlib/Docs/filter/highpass.ipynb,sha256=-sT6-xH9zV7mR6wWZ9Jnqt9lbUEajGafbhGvUVY98IY,40181
+neverlib/Docs/filter/scipy_filter_family.ipynb,sha256=dLhf4BG3KF6jlfiPKeq6Rl5DrUnx0jDx74an4J7ktGk,79092
+neverlib/Docs/vad/VAD_Energy.ipynb,sha256=qqw6_YwRGAbMcU2_F-1XXomU-y42HDY9WYCMxQVvD58,317091
+neverlib/Docs/vad/VAD_Silero.ipynb,sha256=LREAdVkgdKW_XB5N6SFkHHCRqTkkQxigWOFH9Vhxops,303837
+neverlib/Docs/vad/VAD_WebRTC.ipynb,sha256=n5lmmFEnrr5ESigMq_yAwTdVz6jaD84fHwEIf5JnOUg,324763
+neverlib/Docs/vad/VAD_funasr.ipynb,sha256=-4KVReX7IqKfufBHk0oTEYNfzaqlJE5mDuYC8TGhv7U,251035
+neverlib/Docs/vad/VAD_rvADfast.ipynb,sha256=YszYIEG_qVUU2hzvbraY4y5fdMToT--50Za1A3IBozc,252432
+neverlib/Docs/vad/VAD_statistics.ipynb,sha256=wT0k_91YUpLLIt6LZMKrjvJLk4kz8g-fZdBvVH07O2k,346246
+neverlib/Docs/vad/VAD_tenVAD.ipynb,sha256=w8oOBVeabW44Fw7TF6CSxIqa3u1gGydoMuWSxE7slaA,351893
+neverlib/Docs/vad/VAD_vadlib.ipynb,sha256=m55oKqOGeMOSgmQlbMkOR6zVh5_Hn6SIocHi6mOtg1k,300998
+neverlib/Docs/vad/VAD_whisper.ipynb,sha256=P78NqxCfwbbEJYQsqA1NV8vpxQxWNxy2lDX85zO_yD4,364207
+neverlib/QA/gen_init.py,sha256=9QysSB2vk1OR9FmuuKcFtShtiJeCTnvvg6RBlxOUcQU,8127
+neverlib/QA/get_fun.py,sha256=-UP2FOm3jB_138ntpbsW0eG1S0tJ0d90NqI6f95ryYg,541
 neverlib/QA/html2markdown.py,sha256=ZiXvpwcJ_QBhIR6aetaMOmktWHtd_F7Ed07Deo3qM4c,669
-neverlib/audio_aug/HarmonicDistortion.py,sha256=iA6dY42pqA_4I1K4CX1GSqe1Y0urtprtQ9RuB_V4hXA,2382
+neverlib/audio_aug/HarmonicDistortion.py,sha256=MqbfcdWJLtl_WGloQYDa6fIB6QCgukYdjoxsj8X03kk,2706
 neverlib/audio_aug/TFDrop.py,sha256=HDLf5qfqMT73-dxKder0v0AT7b0FYsSlexbbh3sL2iM,987
 neverlib/audio_aug/TFMask.py,sha256=Fakx5YTj88bZEdj_w3aH9Z9AhEGzGq01TZcnjF4v4BU,1769
-neverlib/audio_aug/__init__.py,sha256=BCQf6gQbw8i2nXRc8Cf_4-zU4LvZaCS_bUR6BHohC4M,223
-neverlib/audio_aug/audio_aug.py,sha256=OxxZ2R5ClilAod0tX3nGD2PoakuonNcaMIqfAw_Aafc,16506
-neverlib/audio_aug/clip_aug.py,sha256=fm24KrilyvuIV3oD5mFaUsmNDOEq9VKBMFJ9NtYARkI,1071
-neverlib/audio_aug/coder_aug.py,sha256=lRUx8jwKev8lio2op2X41qv6mMO9uxskcVrR1xFE1MM,7628
-neverlib/audio_aug/coder_aug2.py,sha256=QlSieScNqqZ80mAzk22OlLCdiC81H3dVdt4z3cOVnW0,4305
-neverlib/audio_aug/loss_packet_aug.py,sha256=Ch5GLyF_NqCGzC6Qt3JEu6qp9A6HvYc4zGCUkz9QEUc,4825
-neverlib/audio_aug/quant_aug.py,sha256=GHSpUXnMEjmcituQfUEBESPuhDl3Ql2vQkCOr1wTk7U,2381
+neverlib/audio_aug/__init__.py,sha256=5mBg5p8aDHvOPlRSmR-ojGhtxaJTFCmCZUltaj2RPAs,3313
+neverlib/audio_aug/audio_aug.py,sha256=5Eqtx_v2RLtNEwh1gTyfqSHBirwz1JCgDrjgt4WYBlY,16674
+neverlib/audio_aug/clip_aug.py,sha256=xZi89AtdOgUpX7W4x4_UiZFeK-oCWktueoWSEAY19hU,1041
+neverlib/audio_aug/coder_aug.py,sha256=1JtNadfUVbOw8Xg3vpp0cTl87HHuDedHZ3zbUZ2fWW0,8347
+neverlib/audio_aug/coder_aug2.py,sha256=wniOuOWb3vLqgi8N-oDEfTHuEtQtWZ5O4HhmUfflIlM,4733
+neverlib/audio_aug/loss_packet_aug.py,sha256=z0H6u4ug6FAd2beVYeUQR24GiDg-dfdeEhOTPpGiMms,4862
+neverlib/audio_aug/quant_aug.py,sha256=yUH28tED-oYJxrD3z4rjitDKM6S1ZDtkHtjM2-NSSZY,2608
+neverlib/data/000_short_enhance.wav,sha256=TUZSjHareIY3BFlgZiDuffzirpxnEKagnQDVwDYLdgk,216356
+neverlib/data/3956_speech.wav,sha256=wehCr85ITMOmkQWi1DnjRzb2ggC-XJUftZ3_9sARvS8,2977476
+neverlib/data/3956_sweep.wav,sha256=DoLnlIkYGSuraIE7nWK4nAvmgGWWW4VuhI7xDoMrLys,813832
+neverlib/data/vad_example.wav,sha256=xvcEvjmdjeZO-1fT7u0m0EuiJAqeXUWjBWewDWd8guY,216812
+neverlib/data/white.wav,sha256=JJ3aaPx8v7WakYU7U--m0kO1qUkDSMOrOrPKi6RqAA0,325086
+neverlib/data/white_EQ.wav,sha256=UN1W0hH_4JInnye9vIsQlagVXM-rnJPd1j7A_RIia8c,325086
+neverlib/data/white_matched.wav,sha256=h9vD-2q1eKw9s8pVUoIeXXjeKEC-VRiNABCY-CYcUQ0,115514
 neverlib/data_analyze/README.md,sha256=jqPmD--kinoTqlcpu51teospu9p_ijjtjLdFGTMnBc8,6051
-neverlib/data_analyze/__init__.py,sha256=wTs_8Ppvkk3LbQB0WwHvd-XVYZ_0rhJVcUWmqWlG1PQ,487
-neverlib/data_analyze/dataset_analyzer.py,sha256=V4eK1rjR1gO3V_HC7wlSBotoCApmQdlK52CaSgAG-o8,22909
-neverlib/data_analyze/quality_metrics.py,sha256=Z57TipRlUBne7b0hoyLmd8erbruR2JMDJuh4pbQJeFs,12261
-neverlib/data_analyze/rms_distrubution.py,sha256=o2cpa-25e_2RFYlsPb4AXYgjSpk2sKSOOJkXt93kcy0,1836
-neverlib/data_analyze/spectral_analysis.py,sha256=ItsAf_KBuWwELOMHnX836_AgDUeeB0aIzmXKj0LwrXA,6206
-neverlib/data_analyze/statistics.py,sha256=H60D5JqMdkE3b9Qu8XgZjQUKUPCPl0rFiERJy2U1r3o,13314
-neverlib/data_analyze/temporal_features.py,sha256=TrKaJ-XgrqjtCDGvQ6zIelIBz2M1cVSYn8wLTPa95Og,2689
-neverlib/data_analyze/visualization.py,sha256=MAjkju2hyM-5zczG3Sn_PXonjuxjeieHuaEWFDSYnNY,15101
+neverlib/data_analyze/__init__.py,sha256=3Gl_o2s9OYmy1r7UZLxKZGwwOXJYuQ__F1RM578lvAI,2781
+neverlib/data_analyze/dataset_analyzer.py,sha256=JawpMrahP2YD9mX6kIGJrBRtC7sqYJJdY1R5pGBUDDY,21902
+neverlib/data_analyze/quality_metrics.py,sha256=wOivyQ4JXdyiq1STLCSdBDtoW8Kju-Zc1RZMyPNmNjY,11726
+neverlib/data_analyze/rms_distrubution.py,sha256=EpK9s7WJLtJHXd1xD8SvuiyPVTguouYVHyS7Lha2Qag,1526
+neverlib/data_analyze/spectral_analysis.py,sha256=-QZGSvopovLaSh7OcJLYKFH9YLIp_THXUEV3uOreHz0,5894
+neverlib/data_analyze/statistics.py,sha256=9b9S_7eBoklNfz9cRAs8oWlRnDSjuark4SwTrdFkAGw,12957
+neverlib/data_analyze/temporal_features.py,sha256=qrxA0Uh-DxRPbuILQle66AAgv4SgwiLoPTIR9Q2_Jz4,3065
+neverlib/data_analyze/visualization.py,sha256=kaJBfh1ixlGeVfr4yNRfZlzTvfhbdnIW4LOhbGqwYKM,16439
 neverlib/filter/README.md,sha256=X1VQRnSxzjkeR_16ylbAqRbYLAlf4c5stkHzmWlCzlo,3801
-neverlib/filter/__init__.py,sha256=wCkO_Z2wPw1SnPZ-O0fYQ1r5PDqhidmZqHTE32icSJ8,445
+neverlib/filter/__init__.py,sha256=oQJLBqxGpC1T-DmHbcSceY9Ir31VXqknzoRNQRAGChI,1019
 neverlib/filter/biquad.py,sha256=EEGAqGwTQGG5O49Q855hb475WVX0oOu3zq-Gn_ppIto,1438
-neverlib/filter/common.py,sha256=peGja9A_Lcdvv6gzuOQAhuH9UwpQ3ZVwDSvVMJf_LWo,1408
+neverlib/filter/common.py,sha256=9FD3VKwRpe_IdQujt2AJjlMJ_WR-YNEY8OmhOQUDDO8,1953
 neverlib/filter/core.py,sha256=qr-0IGEEpiSUFgo_uVOXJLLZeaSDFlALzg_b8mEivrY,13091
 neverlib/filter/auto_eq/README.md,sha256=-qcqLxIQPo31YfzABHK-_tcqksLdOTHz8ZG3izz46Ug,4968
-neverlib/filter/auto_eq/__init__.py,sha256=G8hPMz8bzjCYamqcytiGtpe7bSd4YTHVGXUbuK5_zmg,872
-neverlib/filter/auto_eq/de_eq.py,sha256=DqXPyvwO_Kzkcrg5DInGCCKgl2Q8NxeV88LsNvvZAqQ,16444
+neverlib/filter/auto_eq/__init__.py,sha256=RWgAXvBWBDboBxzlPBQJWwQLPctniIAZBXZRQAC_QFw,2190
+neverlib/filter/auto_eq/de_eq.py,sha256=XlbFWDPOdGHI97fbU9wXd4h3Aiosv1T5k_e-VEUcDMQ,16411
 neverlib/filter/auto_eq/freq_eq.py,sha256=1b5hnoqUy1zxVd2WSNqhpokAgJo0xTRwR5AyVPaMr3E,3494
 neverlib/filter/auto_eq/ga_eq_advanced.py,sha256=qu9J5ugWeEAcXboV9Fv1g60bMOkIebw9ZwYT_zQq5pI,23458
 neverlib/filter/auto_eq/ga_eq_basic.py,sha256=gbPqJcimrThzhCjgWkg4DuWpeswRRqxNKMC4I07rp6g,15431
-neverlib/metrics/dnsmos.py,sha256=tXDxd0ToEjbO8cYMyAF50mV6FxyK6oJ1i4_5Yi6srjI,4753
+neverlib/metrics/__init__.py,sha256=NCE7SOoA2UXu4aVmiF0oWvvdS9RaqR9tSY7PZjzDNew,1628
+neverlib/metrics/dnsmos.py,sha256=xfrKxYR9mMDkr2HQ7AT_7V-TtdRpy2MybjsJ2AuLXus,4590
 neverlib/metrics/lpc_lsp.py,sha256=OXKfillGKo55M2aa7LzyvDGcjtOxdOJquWgqC1yV4Ho,3710
-neverlib/metrics/snr.py,sha256=cr776eQgg4Z0uYihFMQq9PtBtprsjvs95nGH_GsmTko,6212
-neverlib/metrics/spec.py,sha256=4jrmf5dynkLkXV6PxERQQK7HbKE6euw0T85aJSZtro4,5131
-neverlib/metrics/test_pesq.py,sha256=J3b0do3wPaj6Fv4WalYAEebtX_nhquhItCf7041I2tI,1252
+neverlib/metrics/snr.py,sha256=l8cYOUuEYeKc5LzQ3q5n4-wql3PcuJfEYcsjBAEQt5w,6360
+neverlib/metrics/spec.py,sha256=OtiHaoHzRuxHtLSS5HVmaisJsD2SPi13T3MphGyeUHc,5442
+neverlib/metrics/test_pesq.py,sha256=nrvd5p3JnMO5jgAuFwmm4rNoZ7riczsB8iFu1Jx8Gxs,1211
 neverlib/metrics/time.py,sha256=MSUdaT3WvFRnL_wvjZEGjwcVrsy7KwArz3hLkYcXF7s,1292
-neverlib/tests/__init__.py,sha256=PITL4btOVji1rexFP35A20v2gcLqc6vmGWiF-_5ywnI,27
+neverlib/metrics/DNSMOS/bak_ovr.onnx,sha256=XzNckJlGGBUBkqZWpHS8-KnLztvEeWVJS6jaeWBdEwg,742375
+neverlib/metrics/DNSMOS/model_v8.onnx,sha256=kkZIDFhWe8av_UIAk4537vSUaMi8ftN3bRCcB0VvbpE,224860
+neverlib/metrics/DNSMOS/sig.onnx,sha256=0vvbKTvCNm37rit0d8SQ-YHSSotEBe_TwReHVpxlSdc,742203
+neverlib/metrics/DNSMOS/sig_bak_ovr.onnx,sha256=Jp--vbUTqiPN37tZNULsxUAoSpGEmsUFFocOGsePbt0,1157965
+neverlib/metrics/pDNSMOS/sig_bak_ovr.onnx,sha256=njoZdEnKIXfwmXr-w71riQEXzi8XuJ1u6n-g1HJyyBw,1157962
+neverlib/metrics/pesq_c/PESQ,sha256=f8qbES1y_94XvHgddOpVqOu0aJBym0z2FXvwq1egBGQ,89400
+neverlib/metrics/pesq_c/dsp.c,sha256=N81r8Hdt-xCUW69ALvECknZHThEhah4okjnxIi1T8Ug,15233
+neverlib/metrics/pesq_c/dsp.h,sha256=I1mOP3JsTNqyEdhI3W3FRBAOltDJnJpXG0ShXbVXM2E,5457
+neverlib/metrics/pesq_c/pesq.h,sha256=wkqE2Vf6EB4QnP16c8jXM-cTBO2SVvmc9JiRNvbHLNs,9430
+neverlib/metrics/pesq_c/pesqdsp.c,sha256=YlGSRes0qJgCyPwe1Zb5bShjGQnDzRE08Ecpv5y0A1E,33879
+neverlib/metrics/pesq_c/pesqio.c,sha256=S8PLwBfx0oHHVLfZ1jUsGbwwMniFhHNNV8X6bcUxFYU,12930
+neverlib/metrics/pesq_c/pesqmain.c,sha256=NaANjEDJrCFwJBbXErX51ZKtE86SHKdrXLhS0P3TbT0,27322
+neverlib/metrics/pesq_c/pesqmod.c,sha256=9stYhCLUShFAd6Zc85nQn57RUKDbS2Q8MrhQFB_-ySA,52999
+neverlib/metrics/pesq_c/pesqpar.h,sha256=XZkwXcwycL8ekK6LQy_PT9Ih2K0zirSPHCMhGKyJExs,20986
+neverlib/tests/__init__.py,sha256=kCV9FZWa7j9g_i6bqb-hEq7pvmWmDz2EMnGX15n7YmE,811
+neverlib/tests/test_imports.py,sha256=3LGZaHZLAz2oJq2ewfRbnWNeAKikHih6d9CIdyqhb0E,547
 neverlib/tests/test_preprocess.py,sha256=GHj2PvlG8chJlV-zpRfy8IYlTXzGkn5heO9ipy6Xe20,1003
 neverlib/tests/test_vad.py,sha256=TjBuB_qPooflrjkkvoy19HySdBo-MiVeb5yTmLGBJvM,415
-neverlib/utils/__init__.py,sha256=Vct3J6mpfmpJwOZWdFyDp0lcf3mbUgSxnwTBiS60qds,259
-neverlib/utils/audio_split.py,sha256=LP08L4VMTKWmus86K0PrFqXWcsGkmAj4gVl2Uqls_c0,12152
-neverlib/utils/checkGPU.py,sha256=Wye2UovtVK6Fk8W4wZ3dqaYrdZc30WyW5iGa-6Ouxf0,4075
+neverlib/utils/__init__.py,sha256=A969zG3BBrSVtoZFsm60PolCaH0BI0PflUUubqfVT8M,2727
+neverlib/utils/audio_split.py,sha256=tDWw36FXMIVOZ08PC9KQTYB3Zz_doFcP1ugYdpLkQjQ,12368
+neverlib/utils/checkGPU.py,sha256=OkztJZJxncqSSIttxISpLSgfqa9xjXOaHIuMlRNwX-4,4393
+neverlib/utils/lazy_expose.py,sha256=3h1LidRoab_ylv574-dOBjnJpOKWgLFgXpTWrvqce9E,1027
 neverlib/utils/lazy_module.py,sha256=JdEdAYnbHmolB-hktrcuOlzR4Ee5jgu6V0XjDNqioVM,3995
 neverlib/utils/message.py,sha256=XV7m0yUsR7Zq-olS-vL1oUEatSgh-Am8pyB_QPLzQok,4121
-neverlib/utils/utils.py,sha256=N28PETG0hbkCYvY_SAWa-FbTdXpApFDXZr4wSH6O26k,14073
-neverlib/vad/PreProcess.py,sha256=syd-s4TiQeqvLeQqQRzTzSqeNuMdWnZEIywX24H4Vro,2108
+neverlib/utils/utils.py,sha256=rsKSOuo__ISdmTe1AQhNqFD8ENHl8A60aDEoGUTiBlE,15179
+neverlib/vad/PreProcess.py,sha256=oib4iRfsUXp5U67pKzJF8k53rqjo8NopK_9LW4O8Mqk,2045
 neverlib/vad/README.md,sha256=3aFnGmz3uhg-kQVOGei40Ei3Lx5P71r2rk0Xl8-JZXI,1490
 neverlib/vad/VAD_Energy.py,sha256=ErsiDxn4mH_EOiFBRcoBBRqTUsFfEsvEvRELrdZflkw,2135
 neverlib/vad/VAD_Silero.py,sha256=L9_eO94VQcO3TBdOWypJxnjMl5ZZBYTkL5DR_6APfs4,2324
@@ -456,12 +498,13 @@ neverlib/vad/VAD_funasr.py,sha256=oJqU3VOFT-KXmFV2g8kvT64nHIo5-PxcB4tdb-Ap3Bw,15
 neverlib/vad/VAD_statistics.py,sha256=o310LKoMECBHO6LcqU3vb-uirF6PM2fHbaRautT2w-w,16663
 neverlib/vad/VAD_vadlib.py,sha256=5reZ7blu0BsqqO9WJn8YPIvPQVn8VcFPcJnH1scgEzQ,2228
 neverlib/vad/VAD_whisper.py,sha256=GhBFV-EIS865c-rj2RvM4IUKKG8ZsoD9LCTwrx1Fx2c,1792
-neverlib/vad/__init__.py,sha256=agJBf6Bl7WXbnFLBo9Iu8nj0QRZewvtFagpoXQKdf84,838
-neverlib/vad/class_get_speech.py,sha256=jbeGNhEYSkvAdf3wdA8J504Uy-plln8-Hu2hNUFEyh8,2074
-neverlib/vad/class_vad.py,sha256=XSOOg_TnNXPjaqD3yr9m6_t7jUYQ5NuZJho9lX2JosA,5215
+neverlib/vad/__init__.py,sha256=UflLGnBIUyqIoIuGLThF4vHeKD6pPRMy3mRyXMiUCAk,2035
+neverlib/vad/class_get_speech.py,sha256=s1n24I4P4aTFaQSiyXrh_xAmOChuFZ-wWgrYEE6eCHs,2074
+neverlib/vad/class_vad.py,sha256=ao_20-vyzcI8CxEcvcA_-HoRPTiPEtfuKor2_YWEbz0,5212
+neverlib/vad/img.png,sha256=eLlaUgDnJNyleWZwW8sNv3eXaeaGoXwhFUZCCDJh9u8,179778
 neverlib/vad/utils.py,sha256=rEWEzGv2E_iTHIdQxY361iEW4Hq9MRDwkMBQMTA9mGw,3049
-neverlib-0.2.6.dist-info/licenses/LICENSE,sha256=h-U7vhFdQhieyaNCiA_utrRNMk1rjfrBAUJVodgkfsw,1096
-neverlib-0.2.6.dist-info/METADATA,sha256=how_JqPsfEeg9xfAqbPvQYcAXTcHr4vvrjiPQE6yjBA,2811
-neverlib-0.2.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-neverlib-0.2.6.dist-info/top_level.txt,sha256=QqwYFuDiY_iFTz0Kx8av6zKCP_s4M5NiMTNsIXOy8Po,9
-neverlib-0.2.6.dist-info/RECORD,,
+neverlib-0.2.8.dist-info/licenses/LICENSE,sha256=h-U7vhFdQhieyaNCiA_utrRNMk1rjfrBAUJVodgkfsw,1096
+neverlib-0.2.8.dist-info/METADATA,sha256=8PeHX6no4CgyTvP8c44NjGA4mclVM_22uKbafKoJO9w,2811
+neverlib-0.2.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+neverlib-0.2.8.dist-info/top_level.txt,sha256=QqwYFuDiY_iFTz0Kx8av6zKCP_s4M5NiMTNsIXOy8Po,9
+neverlib-0.2.8.dist-info/RECORD,,