波形数据预处理软件包
prowav的Python项目详细描述
项目
你可以用它来预处理wave文件。
用法
请使用pip安装prowav。
pip install prowav
使用量
prowav可以计算用于批量执行的mfcc谱图和pad
fromprowavimportProWavprowav=ProWav(["path/to/wave/data_1.wav","path/to/wave/data_2.wav"])frame_width=20# the length of a frame (ms)stride_width=20# the frame interval (ms)n_mfcc=26# the number of features by mfcc features (If you want to use mfcc preprocessing, you should specify this value) mode='MFCC'window_func='hamming'# the name for window functiondata=prowav.prepro(frame_width=frame_width,stride_width=stride_width,mode=mode,n_mfcc=n_mfcc,window_func=window_func)# >> (num_files, num_frames, n_mfcc)
如果要使用fft频谱图，请指定模式“fft”。
prowav=ProWav(["path/to/wave/data_1.wav","path/to/wave/data_2.wav"])frame_width=20stride_width=20mode='fft'window_func='hamming'data=prowav.prepro(frame_width=20,stride_width=20,\ mode=mode,window_func=window_func)# >> (num_files, num_frames, num_features)
也可以使用MEL光谱图。指定模式“mel_spec”
prowav=ProWav(["path/to/wave/data_1.wav","path/to/wave/data_2.wav"])frame_width=50stride_width=50mode='MFCC'n_mfcc=26window_func='hamming'data=prowav.prepro(frame_widh=frame_width,stride_width=stride_width,mode=mode,window_func=window_func,n_mfcc=n_mfcc)
您可以使用零填充或重复填充。
prowav=ProWav(["path/to/wave/data_1.wav","path/to/wave/data_2.wav"])frame_width=50stride_width=50mode='mel_spec'n_mels=50window_func='hamming'data_zero=prowav.prepro(frame_widh=frame_width,stride_width=stride_width,mode=mode,n_mels=n_mels,window_func=window_func,zero_padding=True)# zero padding data_repeat=prowav.prepro(frame_widh=frame_width,stride_width=stride_width,mode=mode,ne_mels=n_mels,window_func=window_func,repeat_padding=True)# repeat padding
只是加载波数据是可能的。
prowav=ProWav(["path/to/wave/data_1.wav","path/to/wave/data_2.wav"])prowav.load_wav()# loading wav file into this class.prowav.data# the list of ndarray. Raw data are listed.
您可以选择并行选项。
prowav.load_wav(parallel=True)prowav.load_wav(parallel=True,verbose=5)
欢迎加入QQ群-->： 979659372
