o 7viC@sLdZddlZddlmZmZddlZddlmZddl m Z dZ e dr?z ddl Z ejZd Z Wney>ed ZYnwed Zid d dddddddd dddddd dd ddddddddddddd dd!d"dddd dddd#ddd$ Zd%d&Zd'd'd'd'd(d)d)ddd*d+ Zd,ed-efd.d/ZedPd0ed,eed1e fd2d3Zd4d5d6d7d8d9d:Ze  ; dQd0eded?ed,eed1eejeffd@dAZdBejdCedDefdEdFZdCedDefdGdHZdBejd,edCedDefdIdJZ e    dRd0edKejdLed?edMee!d,eedCeedDeefdNdOZ"dS)SzCThe new soundfile backend which will become default in 0.8.0 onwardN)OptionalTuple) module_utils) AudioMetaDataF soundfileTz[requires soundfile, but we failed to import it. Please check the installation of soundfile.zFrequires soundfile, but it is not installed. Please install soundfile.PCM_S8PCM_16PCM_24PCM_32 PCM_U8FLOATDOUBLE@ULAWALAW IMA_ADPCMMS_ADPCMGSM610 VOX_ADPCMG721_32G723_24G723_40DWVW_12 ) DWVW_16DWVW_24DWVW_NDPCM_8DPCM_16VORBISALAC_16ALAC_20ALAC_24ALAC_32cCs&|tvr td|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)subtyper/b/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchaudio/_backend/soundfile_backend.py_get_bit_depthEs   r1PCM_SPCM_UPCM_Fr%) rr r rrrrrrr%formatr.cCs|dkrdSt|dS)NFLACUNKNOWN)_SUBTYPE_TO_ENCODINGr-)r5r.r/r/r0 _get_encoding^s r9filepathreturncCs2t|}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) rinfor samplerateframeschannelsr1r.r9r5)r:r5sinfor/r/r0r>ds  r>int8uint8int16int32float32float64)rrr rrr frame_offset num_frames normalizechannels_firstc Cst|d6}|jdks|rd}n|jtvrtd|jt|j}||d|}|j||dd} |j} Wdn1s?wYt | } |rO| } | | 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]`. rWAVrGzUnsupported subtype: NT) always_2d) r SoundFiler5r._SUBTYPE2DTYPE ValueError _prepare_readreadr?torch from_numpyt) r:rJrKrLrMr5file_dtyper@waveform sample_rater/r/r0loadsR   r]rZr=r<c Cs|s.|s#tjdtjdtjdtjdtjdi|}|s!td||S|dkr)dSd|S|d krC|s6dS|dkr>td d|S|d krQ|d vrMdStd |dkre|dvr[dS|dkradStd|dkrs|d vrodStd|dkr|d vr}dStdtd|d)Nrr rrrzUnsupported dtype for wav: r PCM_r2z/wav does not support 8-bit signed PCM encoding.r3Nr z.wav only supports 8-bit unsigned PCM encoding.r4)Nrrz/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 .)rVrDrErFrGrHr-rS)rZr=r<r.r/r/r0_get_subtype_for_wavsR  racCsj|dvr |r d|SdS|dvrtd|d|dkr'|dvr#dStd |d kr-d Std|d ) N)Nr2r^r)r3r4zsph does not support z encoding.rr_z,sph only supports 8-bit for mu-law encoding.rr`)rS)r=r<r/r/r0_get_subtype_for_spheresrbcCs|dkr t|||S|dkr+|rtd|sdS|dkr td|dkr&dSd |S|d vrL|r5td |dus=|d kr?d S|dkrEdStd||dkrRdS|dkr[t||S|dvradStd|)Nwavflaczflac does not support encoding.r r z+flac does not support bits_per_sample > 24.r rr^)oggvorbisz,ogg/vorbis does not support bits_per_sample.rfr%opusOPUSzUnexpected encoding: mp3MPEG_LAYER_IIIsph)nisnistzUnsupported format: )rarSrb)rZr5r=r<r/r/r0 _get_subtype(s2  rnsrcr\ compressionc Cs|jdkrtd|jd|durtdt|dr)|dur$td|}n t|dd }|d vrrRintboolTensorr]rZrarbrnfloatr}r/r/r/r0s              c+