speech_data.py 文件源码

def load_wav_file(name):
    f = wave.open(name, "rb")
    # print("loading %s"%name)
    chunk = []
    data0 = f.readframes(CHUNK)
    while data0:  # f.getnframes()
        # data=numpy.fromstring(data0, dtype='float32')
        # data = numpy.fromstring(data0, dtype='uint16')
        data = numpy.fromstring(data0, dtype='uint8')
        data = (data + 128) / 255.  # 0-1 for Better convergence
        # chunks.append(data)
        chunk.extend(data)
        data0 = f.readframes(CHUNK)
    # finally trim:
    chunk = chunk[0:CHUNK * 2]  # should be enough for now -> cut
    chunk.extend(numpy.zeros(CHUNK * 2 - len(chunk)))  # fill with padding 0's
    # print("%s loaded"%name)
    return chunk