cCi&SrSSKJrJr SSKrSSKJr SSKJ r SSK J r J r J r \ R"\5r"SS \5rS /rg) z$Feature extractor class for EnCodec.)OptionalUnionN)SequenceFeatureExtractor) BatchFeature)PaddingStrategy TensorTypeloggingcX^\rSrSrSrSS/rSS\S\S\S\\S \\4 U4S jjjr \ S \\4S j5r \ S \\4S j5r SS\ \R\\\\R\\\4S\\ \\\4S\\S\\S\\ \\4S\\S \4SjjrSrU=r$)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_mask feature_size sampling_rate padding_valuechunk_length_soverlapc D>[TU]"SXUS.UD6 X@lXPlg)N)rrr)super__init__rr)selfrrrrrkwargs __class__s p/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/encodec/feature_extraction_encodec.pyr EncodecFeatureExtractor.__init__7s) wl_lwpvw, returncbURcg[URUR-5$)N)rintrrs r chunk_length$EncodecFeatureExtractor.chunk_lengthEs-    &t**T-?-??@ @rcURb URcg[S[SUR- UR-55$)Ng?)rrmaxr!r#r"s r chunk_stride$EncodecFeatureExtractor.chunk_strideMs@    &$,,*>q#sT\\1T5F5FFGH Hr raw_audiopadding truncation max_lengthreturn_tensorsc Ub<X`R:wa,[SUSURSURSUS3 5eO-[RSURR S35 U(aU(a [S 5eUcS n[ [U[[45=(a( [US [R[[455nU(a>UVs/sH0n[R"U[RS 9RPM2 nnOU(dC[U[R5(d$[R"U[RS 9nOo[U[R5(aPUR[R"[R 5LaUR#[R5nU(d![R"U5R/n[%U5HupU R&S :a[SU R(35eUR*S:Xa,U R&S:wa[SU R(SS35eUR*S :XdM{U R(SS :wdM[SU R(SS35e Sn [-SU05n UR.bUR0bUcU(a][3SU55n[5[R6"X@R.- 55n U S- UR.-UR0-nOhU(a_[9SU55n[5[R:"X@R.- 55n U S- UR.-UR0-nSnOU n U c.UR=U UUUUS9n U(aU R?S5U S'/n U R?S5H3n UR*S:XaU Sn U RAU R5 M5 XS'UbU RCU5n U $s snf)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: - `'tf'`: Return TensorFlow `tf.constant` objects. - `'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.Tr)dtypez6Expected input shape (channels, length) but got shape r&z$Expected mono audio but example has z channelsz&Expected stereo audio but example has rc3># UHoRSv M g7frNshape.0arrays r 3EncodecFeatureExtractor.__call__.. GYEQYc3># UHoRSv M g7fr5r6r8s rr;r<r=r>r-)r-r,r+return_attention_maskattention_maskr).N)"r ValueErrorloggerwarningr__name__bool isinstancelisttuplenpndarrayasarrayfloat32Tr1float64astype enumeratendimr7rrr(r#minr!floorr'ceilpadpopappendconvert_to_tensors)rr*r+r,r-r.r is_batchedaudioidxexample padded_inputsrnb_steps r__call__ EncodecFeatureExtractor.__call__TsT  $ 2 22 I$P**+,**+9]O1F3 NNVW[WeWeWnWnVop\\  z`a a _G y4- 0 jj1PRPZPZ\acgOh6i  LUVI5E<>>IIVIJy"**$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$7Q)rr)r&i]gNN)NFNNN)rE __module__ __qualname____firstlineno____doc__model_input_namesr!floatrrpropertyr#r(rrJrKrHrFstrrr rr`__static_attributes__ __classcell__)rs@rr r si.(8""*.#'     !  %  AhsmAAIhsmII@D%*$(;?'+zT%[$rzz2BDeDUUVz%c? :;<zTN z SM z !sJ!78 z }z zzrr )retypingrrnumpyrJ!feature_extraction_sequence_utilsrfeature_extraction_utilsrutilsrr r get_loggerrErCr __all__rrrrssH+"I499   H %q6qh % %r