Python對wav文件的重采樣

例如從2channel，4.41k hz 重采樣到 1 channel，16k hz

def downsampleWav(src, dst, inrate=44100, outrate=16000, inchannels=2, outchannels=1):
    import os,wave,audioop
    if not os.path.exists(src):
        print ('Source not found!')
        return False

    if not os.path.exists(os.path.dirname(dst)):
        os.makedirs(os.path.dirname(dst))

    try:
        s_read = wave.open(src, 'r')
        s_write = wave.open(dst, 'w')
    except:
        print ('Failed to open files!')
        return False

    n_frames = s_read.getnframes()
    data = s_read.readframes(n_frames)

    try:
        converted = audioop.ratecv(data, 2, inchannels, inrate, outrate, None)
        if outchannels == 1:
            converted = audioop.tomono(converted[0], 2, 1, 0)
    except:
        print ('Failed to downsample wav')
        return False

    try:
        s_write.setparams((outchannels, 2, outrate, 0, 'NONE', 'Uncompressed'))
        s_write.writeframes(converted)
    except:
        print ('Failed to write wav')
        return False

    try:
        s_read.close()
        s_write.close()
    except:
        print ('Failed to close wav files')
        return False

    return True

　

若in和out都是單通道：

def downsampleWav(src, dst, inrate=48000, outrate=16000, inchannels=1, outchannels=1):
    import os,wave,audioop
    if not os.path.exists(src):
        print ('Source not found!')
        return False

    if not os.path.exists(os.path.dirname(dst)):
        os.makedirs(os.path.dirname(dst))

    try:
        s_read = wave.open(src, 'rb')
        params = s_read.getparams()
        nchannels, sampwidth, framerate, nframes = params[:4]
        print(nchannels,sampwidth, framerate,nframes)
        s_write = wave.open(dst, 'wb')
    except:
        print ('Failed to open files!')
        return False

    n_frames = s_read.getnframes()
    data = s_read.readframes(n_frames)

    try:
        converted = audioop.ratecv(data, 2, inchannels, inrate, outrate, None)
        if outchannels == 1 and inchannels != 1:
            converted = audioop.tomono(converted[0], 2, 1, 0)
    except:
        print ('Failed to downsample wav')
        return False

    try:
        s_write.setparams((outchannels, 2, outrate, 0, 'NONE', 'Uncompressed'))
        s_write.writeframes(converted[0])
    except Exception as e:
        print(e)
        print ('Failed to write wav')
        return False

    try:
        s_read.close()
        s_write.close()
    except:
        print ('Failed to close wav files')
        return False

    return True

 

 

方案二

y為下采樣的結果，類型np.ndarray

You can use Librosa's load() function,

import librosa y, s = librosa.load('test.wav', sr=8000) # Downsample 44.1kHz to 8kHz

The extra effort to install Librosa is probably worth the peace of mind.

Pro-tip: when installing Librosa on Anaconda, you need to install ffmpeg as well, so

pip install librosa conda install -c conda-forge ffmpeg