speech_recognition.py 文件源码

def encode(self, s):
    """Transform a string with a filename into a list of float32.

    Args:
      s: path to the file with a waveform.

    Returns:
      samples: list of int16s
    """
    # Make sure that the data is a single channel, 16bit, 16kHz wave.
    # TODO(chorowski): the directory may not be writable, this should fallback
    # to a temp path, and provide instructions for instaling sox.
    if not s.endswith(".wav"):
      out_filepath = s + ".wav"
      if not os.path.exists(out_filepath):
        call(["sox", "-r", "16k", "-b", "16", "-c", "1", s, out_filepath])
      s = out_filepath
    rate, data = wavfile.read(s)
    assert rate == self._sample_rate
    assert len(data.shape) == 1
    if data.dtype not in [np.float32, np.float64]:
      data = data.astype(np.float32) / np.iinfo(data.dtype).max
    return data.tolist()