Function load_bytes

funasr/utils/load_utils.py:207–237

Convert audio bytes to numpy array. Args: input (bytes): Raw audio bytes. Returns: numpy.ndarray: Decoded audio samples.

(input)

def load_bytes(input):
    """Convert audio bytes to numpy array.

    Args:
        input (bytes): Raw audio bytes.

    Returns:
        numpy.ndarray: Decoded audio samples.
    """
    # Only run the (expensive) frame-rate validation when the payload is an
    # actual audio container (WAV, MP3, OGG, …).  Raw PCM buffers have no
    # recognisable header and would cause pydub to spend ~200 ms before
    # raising an exception that is then silently swallowed anyway.
    if _is_audio_container(input):
        try:
            input = validate_frame_rate(input)
        except Exception:
            pass
    middle_data = np.frombuffer(input, dtype=np.int16)
    middle_data = np.asarray(middle_data)
    if middle_data.dtype.kind not in "iu":
        raise TypeError("'middle_data' must be an array of integers")
    dtype = np.dtype("float32")
    if dtype.kind != "f":
        raise TypeError("'dtype' must be a floating point type")

    i = np.iinfo(middle_data.dtype)
    abs_max = 2 ** (i.bits - 1)
    offset = i.min + abs_max
    array = np.frombuffer((middle_data.astype(dtype) - offset) / abs_max, dtype=np.float32)
    return array


def validate_frame_rate(