U %dA@sdZddlZddlmZmZddlZddlmZddl m Z e rLddl Z ddd d dd d dddddddddd dd dddddd d d dZ ddZddddddddddd ZeedddZed6eeee dddZddd d!d"d#d$Zed7eeeeeeeeejefd'd(d)Zejeed*d+d,Zeed-d.d/Zejeeed0d1d2Zed8eejeeeeeeeeeed3d4d5ZdS)9zCThe new soundfile backend which will become default in 0.8.0 onwardN)OptionalTuple) module_utils) AudioMetaData @ )PCM_S8PCM_16PCM_24PCM_32PCM_U8FLOATDOUBLEULAWALAWZ IMA_ADPCMZMS_ADPCMZGSM610Z VOX_ADPCMZG721_32ZG723_24ZG723_40ZDWVW_12ZDWVW_16ZDWVW_24ZDWVW_NZDPCM_8ZDPCM_16VORBISZALAC_16ZALAC_20ZALAC_24ZALAC_32cCs&|tkrtd|dt|dS)NzThe z subtype is unknown to TorchAudio. As a result, the bits_per_sample attribute will be set to 0. If you are seeing this warning, please report by opening an issue on github (after checking for existing/closed ones). You may otherwise ignore this warning.r)_SUBTYPE_TO_BITS_PER_SAMPLEwarningswarnget)subtyperH/tmp/pip-unpacked-wheel-lbdmvq91/torchaudio/backend/soundfile_backend.py_get_bit_depth5s  rPCM_SPCM_UPCM_Frrr) rrrrrrrrrrformatrcCs|dkr dSt|dS)NZFLACUNKNOWN)_SUBTYPE_TO_ENCODINGrr#rrr _get_encodingNsr')filepathr$returncCs2t|}t|j|j|jt|jt|j |jdS)agGet signal information of an audio file. Note: ``filepath`` argument is intentionally annotated as ``str`` only, even though it accepts ``pathlib.Path`` object as well. This is for the consistency with ``"sox_io"`` backend, which has a restriction on type annotation due to TorchScript compiler compatiblity. Args: filepath (path-like object or file-like object): Source of audio data. format (str or None, optional): Not used. PySoundFile does not accept format hint. Returns: AudioMetaData: meta data of the given audio. )bits_per_sampleencoding) soundfileinfor samplerateframesZchannelsrrr'r$)r(r$sinforrrr-Ts  r-Zint8uint8int16int32float32float64)rrrrrrT)r( frame_offset num_frames normalizechannels_firstr$r)c Cst|dd}|jdks|r"d}n&|jtkr>td|jn t|j}||d|}|j||dd} |j} W5QRXt | } |r| } | | fS)a Load audio data from file. Note: The formats this function can handle depend on the soundfile installation. This function is tested on the following formats; * WAV * 32-bit floating-point * 32-bit signed integer * 16-bit signed integer * 8-bit unsigned integer * FLAC * OGG/VORBIS * SPHERE 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. Note: ``filepath`` argument is intentionally annotated as ``str`` only, even though it accepts ``pathlib.Path`` object as well. This is for the consistency with ``"sox_io"`` backend, which has a restriction on type annotation due to TorchScript compiler compatiblity. Args: filepath (path-like object or file-like object): Source of audio data. frame_offset (int, optional): 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): Not used. PySoundFile does not accept format hint. Returns: (torch.Tensor, int): Resulting Tensor and sample rate. If the input file has integer wav format and normalization is off, then it has integer type, else ``float32`` type. If ``channels_first=True``, it has `[channel, time]` else `[time, channel]`. rZWAVr4zUnsupported subtype: NT)Z always_2d) r,Z SoundFiler$r_SUBTYPE2DTYPE ValueErrorZ _prepare_readreadr.torchZ from_numpyt) r(r7r8r9r:r$file_dtyper/Zwaveform sample_raterrrload{sR   rD)rBr+r*c Cs|s\|sFtjdtjdtjdtjdtjdi|}|sBtd||S|dkrRdSd|S|d kr|sldS|dkr|td d|S|d kr|d krdStd |dkr|dkrdS|dkrdStd|dkr|d krdStd|dkr|d krdStdtd|ddS)NrrrrrzUnsupported dtype for wav: rPCM_r z/wav does not support 8-bit signed PCM encoding.r!Nrz.wav only supports 8-bit unsigned PCM encoding.r")Nr r z/wav only supports 32/64-bit float PCM encoding.rz(wav only supports 8-bit mu-law encoding.rz'wav only supports 8-bit a-law encoding.zwav does not support .)r?r1r2r3r4r5rr=)rBr+r*rrrr_get_subtype_for_wavs\   rHr+r*cCsn|dkr|rd|SdS|dkr2td|d|dkrN|dkrFdStd |d krZd Std|d dS) N)Nr rEr)r!r"zsph does not support z encoding.rrFz,sph only supports 8-bit for mu-law encoding.rrG)r=rIrrr_get_subtype_for_sphere srJrBr$r+r*cCs|dkrt|||S|dkrV|r(td|s0dS|dkr@td|dkrLdSd |S|d krr|sf|rntd d S|d krt||S|dkrdStd|dS)NZwavZflaczflac does not support encoding.rr z+flac does not support bits_per_sample > 24.rrrE)ZoggZvorbisz5ogg/vorbis does not support encoding/bits_per_sample.rsph)nisnistzUnsupported format: )rHr=rJrKrrr _get_subtypes&  rO)r(srcrCr: compressionr$r+r*c Cs|jdkrtd|jd|dk r.tdt|drR|dkrHtd|}nt|dd }|d krxtd |d krtd t |j |||} |dkr|dkrd}|r| }t j |||| |ddS)a Save audio data to file. Note: The formats this function can handle depend on the soundfile installation. This function is tested on the following formats; * WAV * 32-bit floating-point * 32-bit signed integer * 16-bit signed integer * 8-bit unsigned integer * FLAC * OGG/VORBIS * SPHERE Note: ``filepath`` argument is intentionally annotated as ``str`` only, even though it accepts ``pathlib.Path`` object as well. This is for the consistency with ``"sox_io"`` backend, which has a restriction on type annotation due to TorchScript compiler compatiblity. Args: filepath (str or pathlib.Path): Path to audio file. src (torch.Tensor): Audio data to save. must be 2D tensor. sample_rate (int): sampling rate channels_first (bool, optional): If ``True``, the given tensor is interpreted as `[channel, time]`, otherwise `[time, channel]`. compression (float of None, optional): Not used. It is here only for interface compatibility reson with "sox_io" backend. format (str or None, optional): Override the audio format. When ``filepath`` argument is path-like object, audio format is inferred from file extension. If the file extension is missing or different, you can specify the correct format with this argument. When ``filepath`` argument is file-like object, this argument is required. Valid values are ``"wav"``, ``"ogg"``, ``"vorbis"``, ``"flac"`` and ``"sph"``. encoding (str or None, optional): Changes the encoding for supported formats. This argument is effective only for supported formats, sush as ``"wav"``, ``""flac"`` and ``"sph"``. Valid values are; - ``"PCM_S"`` (signed integer Linear PCM) - ``"PCM_U"`` (unsigned integer Linear PCM) - ``"PCM_F"`` (floating point PCM) - ``"ULAW"`` (mu-law) - ``"ALAW"`` (a-law) bits_per_sample (int or None, optional): Changes the bit depth for the supported formats. When ``format`` is one of ``"wav"``, ``"flac"`` or ``"sph"``, you can change the bit depth. Valid values are ``8``, ``16``, ``24``, ``32`` and ``64``. Supported formats/encodings/bit depth/compression are: ``"wav"`` - 32-bit floating-point PCM - 32-bit signed integer PCM - 24-bit signed integer PCM - 16-bit signed integer PCM - 8-bit unsigned integer PCM - 8-bit mu-law - 8-bit a-law Note: Default encoding/bit depth is determined by the dtype of the input Tensor. ``"flac"`` - 8-bit - 16-bit (default) - 24-bit ``"ogg"``, ``"vorbis"`` - Doesn't accept changing configuration. ``"sph"`` - 8-bit signed integer PCM - 16-bit signed integer PCM - 24-bit signed integer PCM - 32-bit signed integer PCM (default) - 8-bit mu-law - 8-bit a-law - 16-bit a-law - 24-bit a-law - 32-bit a-law zExpected 2D Tensor, got zD.Nzr`save` function of "soundfile" backend does not support "compression" parameter. The argument is silently ignored.writez0`format` is required when saving to file object.rGr6)Nrrr r r zInvalid bits_per_sample.r zvSaving audio with 24 bits per sample might warp samples near -1. Using 16 bits per sample might be able to avoid this.)rMrNrLZNIST)filedatar.rr$)ndimr=rrhasattr RuntimeErrorlowerstrsplitrOrBr@r,rS) r(rPrCr:rQr$r+r*extrrrrsave.s.f   r])N)rr6TTN)TNNNN)__doc__rtypingrrr?Ztorchaudio._internalrZ _mod_utilscommonrZis_soundfile_availabler,rrr&rZr'Zrequires_soundfiler-r<intboolZTensorrDrBrHrJrOfloatr]rrrrs      c+