torchaudio.load() 和 librosa.load() 的区别

librosa.load() 参数如下：（得到的音频序列是numpy序列）

"""音频路径"""
path : string, int, pathlib.Path or file-like object
        path to the input file.

        Any codec supported by `soundfile` or `audioread` will work.

        Any string file paths, or any object implementing Python's
        file interface (e.g. `pathlib.Path`) are supported as `path`.

        If the codec is supported by `soundfile`, then `path` can also be
        an open file descriptor (int).

"""采样率"""
sr   : number > 0 [scalar]
        target sampling rate

        'None' uses the native sampling rate

"""是否设置为单声道或者多声道"""
mono : bool
        convert signal to mono


"""音频的起始点（单位是秒）"""
offset : float
        start reading after this time (in seconds)


""""读取音频的时长（单位为秒）"""
duration : float
        only load up to this much audio (in seconds)


"""设置音频序列的类型"""
dtype : numeric type
        data type of `y`


"""设置重采样类型"""
res_type : str
        resample type (see note)

        .. note::
            By default, this uses `resampy`'s high-quality mode ('kaiser_best').

            For alternative resampling modes, see `resample`

        .. note::
           `audioread` may truncate the precision of the audio data to 16 bits.

           See https://librosa.github.io/librosa/ioformats.html for alternate
           loading methods.


"""返回值两个值（前为音频序列，后为采样率）"""
Returns
    -------
    y    : np.ndarray [shape=(n,) or (2, n)]
        audio time series

    sr   : number > 0 [scalar]
        sampling rate of `y`

torchaudio.load(): 下载的得到的音频序列是tensor类型

常见用法：

clean_s, fs = torchaudio.load( filepath, frame_offset, num_frames)

filepath 是音频文件路径；

frame_offset 是音频起始点，和librosa不同的是，这里的起始点是采样点数；

num_frames 是音频的帧数；计算公式（wav_length - frame_len）/ frame_hop +1 = num_frames