U %d? @snddlZddlmZmZddlZddlZddlmZddl m Z e ee e dddZ ee e d d d Z de eeeeee eejefdddZddZejjrddlmmZejZejZejZejZne Ze ZeZeZe de ee e dddZ!e de eeeeee eejefdddZ"e de ejeeee#ee ee eedddZ$dS)N)OptionalTuple) module_utils) AudioMetaData)filepathformatreturncCstd|dSNz Failed to fetch metadata from {} RuntimeErrorr)rrr E/tmp/pip-unpacked-wheel-lbdmvq91/torchaudio/backend/sox_io_backend.py _fail_info sr)rr cCstd|dSr r )fileobjrr r r_fail_info_fileobjsrT)r frame_offset num_frames normalizechannels_firstrr cCstd|dS)NzFailed to load audio from {}r )rrrrrrr r r _fail_loadsrcOstd|dS)NzFailed to load audio from )r )rargskwargsr r r_fail_load_fileobj srcCstjsXt|drN|dkr&t||Stj||}|dk rDt|St||St |}tj j ||}|dk rxt|St ||S)aGet signal information of an audio file. Args: filepath (path-like object or file-like object): Source of audio data. When the function is not compiled by TorchScript, (e.g. ``torch.jit.script``), the following types are accepted; * ``path-like``: file path * ``file-like``: Object with ``read(size: int) -> bytes`` method, which returns byte string of at most ``size`` length. When the function is compiled by TorchScript, only ``str`` type is allowed. Note: * When the input type is file-like object, this function cannot get the correct length (``num_samples``) for certain formats, such as ``mp3`` and ``vorbis``. In this case, the value of ``num_samples`` is ``0``. * This argument is intentionally annotated as ``str`` only due to TorchScript compiler compatibility. format (str or None, optional): Override the format detection with the given format. Providing the argument might help when libsox can not infer the format from header or extension. Returns: AudioMetaData: Metadata of the given audio. readmp3N)torchjit is_scriptinghasattr_fallback_info_fileobj torchaudio _torchaudioZget_info_fileobjrosfspathopsZsox_io_get_info_fallback_info)rrsinfor r rinfo2s#     r)cCstjslt|drb|dkr.t||||||Stj||||||}|dk rP|St||||||St |}tj j ||||||}|dk r|St ||||||S)aLoad audio data from file. Note: This function can handle all the codecs that underlying libsox can handle, however it is tested on the following formats; * WAV, AMB * 32-bit floating-point * 32-bit signed integer * 24-bit signed integer * 16-bit signed integer * 8-bit unsigned integer (WAV only) * MP3 * FLAC * OGG/VORBIS * OPUS * SPHERE * AMR-NB To load ``MP3``, ``FLAC``, ``OGG/VORBIS``, ``OPUS`` and other codecs ``libsox`` does not handle natively, your installation of ``torchaudio`` has to be linked to ``libsox`` and corresponding codec libraries such as ``libmad`` or ``libmp3lame`` etc. By default (``normalize=True``, ``channels_first=True``), this function returns Tensor with ``float32`` dtype, and the shape of `[channel, time]`. .. warning:: ``normalize`` argument does not perform volume normalization. It only converts the sample type to `torch.float32` from the native sample type. When the input format is WAV with integer type, such as 32-bit signed integer, 16-bit signed integer, 24-bit signed integer, and 8-bit unsigned integer, by providing ``normalize=False``, this function can return integer Tensor, where the samples are expressed within the whole range of the corresponding dtype, that is, ``int32`` tensor for 32-bit signed PCM, ``int16`` for 16-bit signed PCM and ``uint8`` for 8-bit unsigned PCM. Since torch does not support ``int24`` dtype, 24-bit signed PCM are converted to ``int32`` tensors. ``normalize`` argument has no effect on 32-bit floating-point WAV and other formats, such as ``flac`` and ``mp3``. For these formats, this function always returns ``float32`` Tensor with values. Args: filepath (path-like object or file-like object): Source of audio data. When the function is not compiled by TorchScript, (e.g. ``torch.jit.script``), the following types are accepted; * ``path-like``: file path * ``file-like``: Object with ``read(size: int) -> bytes`` method, which returns byte string of at most ``size`` length. When the function is compiled by TorchScript, only ``str`` type is allowed. Note: This argument is intentionally annotated as ``str`` only due to TorchScript compiler compatibility. frame_offset (int): Number of frames to skip before start reading data. num_frames (int, optional): Maximum number of frames to read. ``-1`` reads all the remaining samples, starting from ``frame_offset``. This function may return the less number of frames if there is not enough frames in the given file. normalize (bool, optional): When ``True``, this function converts the native sample type to ``float32``. Default: ``True``. If input file is integer WAV, giving ``False`` will change the resulting Tensor type to integer type. This argument has no effect for formats other than integer WAV type. channels_first (bool, optional): When True, the returned Tensor has dimension `[channel, time]`. Otherwise, the returned Tensor's dimension is `[time, channel]`. format (str or None, optional): Override the format detection with the given format. Providing the argument might help when libsox can not infer the format from header or extension. Returns: (torch.Tensor, int): Resulting Tensor and sample rate. If the input file has integer wav format and ``normalize=False``, then it has integer type, else ``float32`` type. If ``channels_first=True``, it has `[channel, time]` else `[time, channel]`. rrN) rrrr _fallback_load_fileobjr"r#load_audio_fileobjr$r%r&Zsox_io_load_audio_file_fallback_load)rrrrrrretr r rloadks6a   r.rsrcZ sample_rater compressionrencodingZbits_per_samplec Cs\tjss   8 z