P/jCdZddlZddlmZmZddlZddlmZddl m Z dZ ejdr ddl Z ejZd Z nej"d Zid d dddddddd dddddd dd ddddddddddddd dd!d"dddd dddd#ddd$ Zd%Zd&d&d&d&d'd(d(ddd)d* Zd+ed,efd-ZedGd.ed+eed/e fd0Zd1d2d3d4d5d6d7Ze dHd.ed8ed9ed:ed;ed+eed/eej6effd<Zd=ej:d>ed?efd@Zd>ed?efdAZd=ej:d+ed>ed?efdBZ e dId.edCej6dDed;edEee!d+eed>eed?eefdFZ"y#e$rej"d ZY'wxYw)JzCThe 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_32cp|tvrtjd|dtj|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)subtypes h/root/repos/pocs/video-evals/.venv/lib/python3.12/site-packages/torchaudio/_backend/soundfile_backend.py_get_bit_depthr2Es=11 7)5 5 ' * *7A 66PCM_SPCM_UPCM_Fr&) r r r rrrrrrr&formatr0c:|dk(rytj|dS)NFLACUNKNOWN)_SUBTYPE_TO_ENCODINGr/)r7r0s r1 _get_encodingr<^s    # #GY 77r3filepathreturnc tj|}t|j|j|j t |jt|j|jS)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 samplerateframeschannelsr2r0r<r7)r=r7sinfos r1rBrBdsT& NN8 $E    &u}}5u||U]];  r3int8uint8int16int32float32float64)r rr rrr frame_offset num_frames normalizechannels_firstctj|d5}|jdk7s|rd}n=|jtvrt d|jt|j}|j |d|}|j||d} |j} dddtj } |r| j} |  fS#1swY4xYw)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]`. rWAVrKzUnsupported subtype: NT) always_2d) r SoundFiler7r0_SUBTYPE2DTYPE ValueError _prepare_readreadrCtorch from_numpyt) r=rMrNrOrPr7file_dtyperDwaveform sample_rates r1loadrasd   Xs + 'u <<5 IE ]]. 04U]]ODE E"5==1E$$\4D::fet:<&&  ')H::< [   ' 's BCCr^rAr@c |s|sstjdtjdtjdtjdtj dij |}|std||S|dk(ryd|S|d k(r|sy|dk(r td d|S|d k(r|d vrytd |dk(r|dvry|dk(rytd|dk(r|d vrytd|dk(r|d vrytdtd|d)Nrr rrrzUnsupported dtype for wav: r PCM_r4z/wav does not support 8-bit signed PCM encoding.r5Nr z.wav only supports 8-bit unsigned PCM encoding.r6)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 .)rZrHrIrJrKrLr/rW)r^rAr@r0s r1_get_subtype_for_wavrfsL  X X X w x  c%j  #>ug!FGGN a o&''7 a NO Oo&''7 i 'IJJ7 j ( b JKK6 i 'CDD6 i 'BCC ,XJa8 99r3c|dvr |rd|SdS|dvrtd|d|dk(r|dvrytd |d k(ry td|d ) N)Nr4rcr)r5r6zsph does not support z encoding.rrdz,sph only supports 8-bit for mu-law encoding.rre)rW)rAr@s r1_get_subtype_for_sphererhs|?"+:o&'HH%%0 *EFF6 i 'GHH6 ,XJa8 99r3c6|dk(r t|||S|dk(r,|r td|sy|dkDr td|dk(rdSd |S|d vr)|r td ||d k(ry |dk(rytd||dk(ry|dk(r t||S|dvrytd|)Nwavflaczflac does not support encoding.r rz+flac does not support bits_per_sample > 24.r r rc)oggvorbisz,ogg/vorbis does not support bits_per_sample.rmr&opusOPUSzUnexpected encoding: mp3MPEG_LAYER_IIIsph)nisnistzUnsupported format: )rfrWrh)r^r7rAr@s r1 _get_subtyperu(s #E8_EE  >? ? R JK K*a/xMtO;L5MM "" KL L  x83 v 0 ;<<  &xAA   +F84 55r3srcr` compressionc|jdk7rtd|jd|tjdt |dr| t d|j }n+t|jdd j }|d vr td |d k(rtjd t|j|||} |dvr|d}|r|j}tj|||| |y)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.re)Nr r rrrzInvalid bits_per_sample.rzvSaving audio with 24 bits per sample might warp samples near -1. Using 16 bits per sample might be able to avoid this.)rsrtrrNIST)filedatarCr0r7)ndimrWr-r.hasattr RuntimeErrorlowerstrsplitrur^r\rrz) r=rvr`rPrwr7rAr@extr0s r1saverDsL xx1}3CHH:R@AA  0 x! >QR Rlln(m!!#&r*00277344"  D 399c8_EG $$eeg OO W]cdr3)N)rr{TTN)TNNNN)#__doc__r-typingrrrZtorchaudio._internalr _mod_utilscommonr_IS_SOUNDFILE_AVAILABLEis_module_availablerno_op_requires_soundfile Exceptionfail_with_messager,r2r;rr<rBrVintboolTensorrar^rfrhrufloatrr3r1rs|I" ;! ":!!+. (.."& 7*66P a b b b   a   R  b A A aqq q!"r#$7>7    8#88 3 :   `!`!`!`! `!  `! SM `! 5<< `!`!F(: (:s(:S(:V :c :C :6 6S6C6RU68  #' "%)DeDe DeDe De % De SM DesmDec]DeDec  :j:: i  sE&&FF