a h5@sdZddlZddlmZmZmZmZddlZd eeeej fe e e e eee eeeej e fd dd Z deeej fej e e eeeeee e eeeeee fdd d d ZdS)z&TorchCodec integration for TorchAudio.N)BinaryIOOptionalTupleUnionT) uri frame_offset num_frames normalizechannels_firstformat buffer_sizebackendreturnc CsFzddlm}Wn.ty>} ztd| WYd} ~ n d} ~ 00|s\ddl} | jdtdd|dkr|ddl} | jd tdd|durddl} | jd tdd|durddl} | jd tddz ||} Wn<ty} z"td |d | | WYd} ~ n d} ~ 00| jj } | dur tdz | } Wn6tyb} ztd| | WYd} ~ n d} ~ 00| j }|dkr||j dkr|r|j ddfn d|j df}t j|t jd| fS|dd|df}|dkr|r|j ddfn d|j df}t j|t jd| fS|dkr,|ddd|f}|s>|dd}|| fS)ae Load audio data from source using TorchCodec's AudioDecoder. .. note:: This function supports the same API as :func:`~torchaudio.load`, and relies on TorchCodec's decoding capabilities under the hood. It is provided for convenience, but we do recommend that you port your code to natively use ``torchcodec``'s ``AudioDecoder`` class for better performance: https://docs.pytorch.org/torchcodec/stable/generated/torchcodec.decoders.AudioDecoder. In TorchAudio 2.9, :func:`~torchaudio.load` will be relying on :func:`~torchaudio.load_with_torchcodec`. Note that some parameters of :func:`~torchaudio.load`, like ``normalize``, ``buffer_size``, and ``backend``, are ignored by :func:`~torchaudio.load_with_torchcodec`. Args: uri (path-like object or file-like object): Source of audio data. The following types are accepted: * ``path-like``: File path or URL. * ``file-like``: Object with ``read(size: int) -> bytes`` method. frame_offset (int, optional): Number of samples to skip before start reading data. num_frames (int, optional): Maximum number of samples to read. ``-1`` reads all the remaining samples, starting from ``frame_offset``. normalize (bool, optional): TorchCodec always returns normalized float32 samples. This parameter is ignored and a warning is issued if set to False. Default: ``True``. 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): Format hint for the decoder. May not be supported by all TorchCodec decoders. (Default: ``None``) buffer_size (int, optional): Not used by TorchCodec AudioDecoder. Provided for API compatibility. backend (str or None, optional): Not used by TorchCodec AudioDecoder. Provided for API compatibility. Returns: (torch.Tensor, int): Resulting Tensor and sample rate. Always returns float32 tensors. If ``channels_first=True``, shape is `[channel, time]`, otherwise `[time, channel]`. Raises: ImportError: If torchcodec is not available. ValueError: If unsupported parameters are used. RuntimeError: If TorchCodec fails to decode the audio. Note: - TorchCodec always returns normalized float32 samples, so the ``normalize`` parameter has no effect. - The ``buffer_size`` and ``backend`` parameters are ignored. - Not all audio formats supported by torchaudio backends may be supported by TorchCodec. r) AudioDecoderz`TorchCodec is required for load_with_torchcodec. Please install torchcodec to use this function.NznTorchCodec AudioDecoder always returns normalized float32 samples. The 'normalize=False' parameter is ignored. stacklevelrzCThe 'buffer_size' parameter is not used by TorchCodec AudioDecoder.z?The 'backend' parameter is not used by TorchCodec AudioDecoder.zCThe 'format' parameter is not supported by TorchCodec AudioDecoder.z"Failed to create AudioDecoder for : z3Unable to determine sample rate from audio metadataz Failed to decode audio samples: )dtype)Ztorchcodec.decodersr ImportErrorwarningswarn UserWarning Exception RuntimeErrormetadata sample_rateZget_all_samplesdatashapetorchzerosfloat32 transpose)rr r r r r rrrerdecoderrZ audio_samplesr Z empty_shaper(D/var/www/auris/lib/python3.9/site-packages/torchaudio/_torchcodec.pyload_with_torchcodec szG ,  & " "  r*) rsrcrr r encodingbits_per_samplerr compressionrc  Cs~zddlm} Wn.ty>} ztd| WYd} ~ n d} ~ 00|dur`ddl} | jdtdd|durddl} | jdtdd|durddl} | jd tdd|d krddl} | jd tdd|durddl} | jd tddt|tjst d t ||j tj kr| }|dkr,t d||jdkr^|rJ|d} n|ddd} n8|jdkr|rv|} n |dd} nt d|jdz| | |d}Wn6ty} ztd| | WYd} ~ n d} ~ 00d}| dur*t| tt frt| }n$ddl} | jdt | dtddz|j||dWn<tyx} z"td|d| | WYd} ~ n d} ~ 00dS)a Save audio data to file using TorchCodec's AudioEncoder. .. note:: This function supports the same API as :func:`~torchaudio.save`, and relies on TorchCodec's encoding capabilities under the hood. It is provided for convenience, but we do recommend that you port your code to natively use ``torchcodec``'s ``AudioEncoder`` class for better performance: https://docs.pytorch.org/torchcodec/stable/generated/torchcodec.encoders.AudioEncoder. In TorchAudio 2.9, :func:`~torchaudio.save` will be relying on :func:`~torchaudio.save_with_torchcodec`. Note that some parameters of :func:`~torchaudio.save`, like ``format``, ``encoding``, ``bits_per_sample``, ``buffer_size``, and ``backend``, are ignored by are ignored by :func:`~torchaudio.save_with_torchcodec`. This function provides a TorchCodec-based alternative to torchaudio.save with the same API. TorchCodec's AudioEncoder provides efficient encoding with FFmpeg under the hood. Args: uri (path-like object): Path to save the audio file. The file extension determines the format. src (torch.Tensor): Audio data to save. Must be a 1D or 2D tensor with float32 values in the range [-1, 1]. If 2D, shape should be [channel, time] when channels_first=True, or [time, channel] when channels_first=False. sample_rate (int): Sample rate of the audio data. channels_first (bool, optional): Indicates whether the input tensor has channels as the first dimension. If True, expects [channel, time]. If False, expects [time, channel]. Default: True. format (str or None, optional): Audio format hint. Not used by TorchCodec (format is determined by file extension). A warning is issued if provided. Default: None. encoding (str or None, optional): Audio encoding. Not fully supported by TorchCodec AudioEncoder. A warning is issued if provided. Default: None. bits_per_sample (int or None, optional): Bits per sample. Not directly supported by TorchCodec AudioEncoder. A warning is issued if provided. Default: None. buffer_size (int, optional): Not used by TorchCodec AudioEncoder. Provided for API compatibility. A warning is issued if not default value. Default: 4096. backend (str or None, optional): Not used by TorchCodec AudioEncoder. Provided for API compatibility. A warning is issued if provided. Default: None. compression (float, int or None, optional): Compression level or bit rate. Maps to bit_rate parameter in TorchCodec AudioEncoder. Default: None. Raises: ImportError: If torchcodec is not available. ValueError: If input parameters are invalid. RuntimeError: If TorchCodec fails to encode the audio. Note: - TorchCodec AudioEncoder expects float32 samples in [-1, 1] range. - Some parameters (format, encoding, bits_per_sample, buffer_size, backend) are not used by TorchCodec but are provided for API compatibility. - The output format is determined by the file extension in the uri. - TorchCodec uses FFmpeg under the hood for encoding. r) AudioEncoderz`TorchCodec is required for save_with_torchcodec. Please install torchcodec to use this function.NzjThe 'format' parameter is not used by TorchCodec AudioEncoder. Format is determined by the file extension.rrzKThe 'encoding' parameter is not fully supported by TorchCodec AudioEncoder.zUThe 'bits_per_sample' parameter is not directly supported by TorchCodec AudioEncoder.rzCThe 'buffer_size' parameter is not used by TorchCodec AudioEncoder.z?The 'backend' parameter is not used by TorchCodec AudioEncoder.z'Expected src to be a torch.Tensor, got z"sample_rate must be positive, got rzExpected 1D or 2D tensor, got zD tensor)rzFailed to create AudioEncoder: zUnsupported compression type z<. TorchCodec AudioEncoder expects int or float for bit_rate.)bit_ratezFailed to save audio to r)Ztorchcodec.encodersr/rrrr isinstancer"Tensor ValueErrortyperr$floatndimZ unsqueezer%rrintZto_file)rr+rr r r,r-rrr.r/r&rr encoderr0r(r(r)save_with_torchcodecsW     &  r9)rrTTNrN)TNNNrNN)__doc__ostypingrrrrr"strPathLiker7boolr2r*r5r9r(r(r(r)sT !