+ j8&~Rt^RIt^RIHt^RIHt^RIHtH t H t ] P!] 4t !RR]4tR.tR#)z$Feature extractor class for EnCodec.N)SequenceFeatureExtractor) BatchFeature)PaddingStrategy TensorTypeloggingcaa]tRt^toRtRR.tR V3RlV3Rlllt]V3RlRl4t]V3RlR l4t RV3R lR llt R t Vt V;t #)EncodecFeatureExtractora Constructs an EnCodec feature extractor. This feature extractor inherits from [`~feature_extraction_sequence_utils.SequenceFeatureExtractor`] which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. Instantiating a feature extractor with the defaults will yield a similar configuration to that of the [facebook/encodec_24khz](https://huggingface.co/facebook/encodec_24khz) architecture. Args: feature_size (`int`, *optional*, defaults to 1): The feature dimension of the extracted features. Use 1 for mono, 2 for stereo. sampling_rate (`int`, *optional*, defaults to 24000): The sampling rate at which the audio waveform should be digitalized expressed in hertz (Hz). padding_value (`float`, *optional*, defaults to 0.0): The value that is used to fill the padding values. chunk_length_s (`float`, *optional*): If defined the audio is pre-processed into chunks of lengths `chunk_length_s` and then encoded. overlap (`float`, *optional*): Defines the overlap between each chunk. It is used to compute the `chunk_stride` using the following formulae : `int((1.0 - self.overlap) * self.chunk_length)`. input_values padding_maskc T<V^8dQhRS[RS[RS[RS[R,RS[R,/#) feature_size sampling_rate padding_valuechunk_length_sNoverlap)intfloat)format __classdict__s"w/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/encodec/feature_extraction_encodec.py __annotate__$EncodecFeatureExtractor.__annotate__4sE         c L<\SV`!RRVRVRV/VBW@nWPnR#)r rrN)super__init__rr)selfr rrrrkwargs __class__s&&&&&&,rr EncodecFeatureExtractor.__init__4s1 wlw-w_lwpvw, rc.<V^8dQhRS[R,/#r returnNr)rrs"rrrCsAAcDjArcnVPfR#\VPVP,4#)N)rrrrs&r chunk_length$EncodecFeatureExtractor.chunk_lengthBs-    &t**T-?-??@ @rc.<V^8dQhRS[R,/#r#r%)rrs"rrrKsIIcDjIrcVPeVPfR#\^\RVP, VP,44#)Ng?)rrmaxrr(r's&r chunk_stride$EncodecFeatureExtractor.chunk_strideJs@    &$,,*>q#sT\\1T5F5FFGH HrcR<V^8dQhRS[PS[S[,,S[S[P,,S[S[S[,,,RS[S[,S[,R,RS[R,RS[R,RS[S[,R,RS[R,RS[ /#) r raw_audiopaddingN truncation max_lengthreturn_tensorsrr$) npndarraylistrboolstrrrrr)rrs"rrrQsyy::U +d2::.>>d5kARRyo-4y4K y $J y j(4/ yTzy yrc  B Ve>W`P8wd-\RV RVP RVP RV R2 4hM-\PRVPP R24V'dV'd \R 4hVfR p\ \V\\34;'d-\V^,\P\\344pV'dAVUu.uF3p\P!V\PR 7PNK5 ppMV'gH\V\P4'g(\P!V\PR 7pMq\V\P4'dRVP\P!\P 4Jd VP#\P4pV'g"\P!V4P.p\%V4FwrV P&^8d\R V P( 24hVP*^8Xd2V P&^8wd!\R V P(R, R24hVP*^8XgKV P(R,^8wgK\RV P(R, R24h Rp \-RV/4p VP.EeVP0eVfV'dn\3RV44p\5\P6!W@P., 44p V ^, VP.,VP0,pMyV'dp\9RV44p\5\P:!W@P., 44p V ^, VP.,VP0,pRpMT p V f3VP=V VVVVR7p V'dV P?R4V R&.p V P?R4F8p VP*^8Xd V R,p V PAV P4K: WR&VeV PCV4p V #uupi)a Main method to featurize and prepare for the model one or several sequence(s). Args: raw_audio (`np.ndarray`, `list[float]`, `list[np.ndarray]`, `list[list[float]]`): The sequence or batch of sequences to be processed. Each sequence can be a numpy array, a list of float values, a list of numpy arrays or a list of list of float values. The numpy array must be of shape `(num_samples,)` for mono audio (`feature_size = 1`), or `(2, num_samples)` for stereo audio (`feature_size = 2`). padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`): Select a strategy to pad the returned sequences (according to the model's padding side and padding index) among: - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single sequence if provided). - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different lengths). truncation (`bool`, *optional*, defaults to `False`): Activates truncation to cut input sequences longer than `max_length` to `max_length`. max_length (`int`, *optional*): Maximum length of the returned list and optionally padding length (see above). return_tensors (`str` or [`~utils.TensorType`], *optional*): If set, will return tensors instead of list of python integers. Acceptable values are: - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return Numpy `np.ndarray` objects. sampling_rate (`int`, *optional*): The sampling rate at which the `audio` input was sampled. It is strongly recommended to pass `sampling_rate` at the forward call to prevent silent errors. Nz3The model corresponding to this feature extractor: z& was trained using a sampling rate of zB. Please make sure that the provided audio input was sampled with z and not .zDIt is strongly recommended to pass the `sampling_rate` argument to `zN()`. Failing to do so can result in silent errors that might be hard to debug.zABoth padding and truncation were set. Make sure you only set one.T)dtypez6Expected input shape (channels, length) but got shape z$Expected mono audio but example has z channelsz&Expected stereo audio but example has r c3F"TFqP^,xK R#5iNshape.0arrays& r 3EncodecFeatureExtractor.__call__.. GYEQY!c3F"TFqP^,xK R#5ir>r@rBs& rrErFrGrHr3)r3r2r1return_attention_maskattention_maskr ).N)"r ValueErrorloggerwarningr __name__r8 isinstancer7tupler5r6asarrayfloat32Tr<float64astype enumeratendimrAr rr-r(minrfloorr,ceilpadpopappendconvert_to_tensors)rr0r1r2r3r4r is_batchedaudioidxexample padded_inputsr nb_steps&&&&&&& r__call__ EncodecFeatureExtractor.__call__QsR  $ 2 22 I$P**+,**+9]O1F3 NNVW[WeWeWnWnVop\\  z`a a _G y4- 0 j jj1PRPZPZ\acgOh6i  LUVI5E<>>IIVIJy"**$E$E 9BJJ?I  2:: . .9??bhhrzzFZ3Z!((4II.001I&i0LC||a #YZaZgZgYh!ijj  A%',,!*; #G VXHYGZZc!dee  A%'--*;q*@ #I'--XZJ[I\\e!fgg 1 #^Y$?@    (T->->-JzOa GY GG bhhz4E4E'EFG%kT->->>ARARR  GY GG bggj3D3D&DEF%kT->->>ARARR & ,    HH%%&- %M0=0A0ABR0S n- $((8G  A%!),    *9 )5n%  %)<<^LMqWs/9R)rr)i]gNN)NFNNN)rP __module__ __qualname____firstlineno____doc__model_input_namesrpropertyr(r-rg__static_attributes____classdictcell__ __classcell__)r rs@@rrrs_.(8  AAII yyyrr)rmnumpyr5!feature_extraction_sequence_utilsrfeature_extraction_utilsrutilsrrr get_loggerrPrNr__all__rrrrysE+I499   H %p6pf % %r