j* SSKrSSKJr SSKJrJr SSKJr SSKJ r SSK J r J r J r SSKJrJrJr \"5(a SSKrSSKJs Jr \"5(aSSKr\ R0"\5r\"S S 9"S S \55rS /rg) N)Any) AudioInputmake_list_of_audio)SequenceFeatureExtractor) BatchFeature)PaddingStrategy TensorTypelogging)is_torch_availableis_torchaudio_availablerequires) torchaudio)backendsc^\rSrSrSr/SQrSU4SjjrSS\S\\ -\ -S\ S-S \S \ \ -S-S \ S-S \ S \ 4SjjrS \\ \44SjrSrU=r$)Xcodec2FeatureExtractor$a Constructs a Xcodec2 feature extractor, which computes mel-filter bank features for the semantic encoder and padded audio for the acoustic encoder. This feature extractor inherits from [`SequenceFeatureExtractor`] which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. Args: feature_size (`int`, *optional*, defaults to 80): The feature dimension of the extracted features. sampling_rate (`int`, *optional*, defaults to 16000): The sample rate at which the audio files should be digitalized expressed in hertz (Hz). padding_value (`float`, *optional*, defaults to 1.0): The value that is used to fill the padding vectors for the mel spectrogram. hop_length (`int`, *optional*, defaults to 320): Number of audio samples encoded per frame. Equivalent to product of downsampling ratios. Needed for acoustic encoder input padding. )input_features input_values padding_maskinput_features_maskc >[TU]"S XUS.UD6 X@l[SUSS9UlSS/URlSUlSUlSUlS Ul g) N) feature_size sampling_rate padding_valueaudiorPi) super__init__ hop_lengthracoustic_encoder_paddermodel_input_namesstride num_mel_bins frame_length frame_shift)selfrrrr%kwargs __class__s C:\Users\johnn\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\LocalCache\local-packages\Python313\site-packages\transformers/models/xcodec2/feature_extraction_xcodec2.pyr$ Xcodec2FeatureExtractor.__init__;sr wl_lwpvw%'?'( $ ;B>9R$$6 Nrpadding max_length truncationreturn_tensorsrdevicereturnc &Ub<X`R:wa,[SUSURSURSUS3 5eO-[RSURR S35 [ U5nUH+n U RS :dM[S U R35e [U5n UV s/sH-n [R"[R"U 5S S S 9PM/ nn URR[SU05UUUUUR SS9n U R#S5n U SSS2SSS24n/n[%U 5GHnU b*['U UR)5R+55OURSnUUR -S- UR -UR -n[-UURS5nUUSS2SU24n[R"UUR S -UR S -4S S 9nUR/U5n[0R2R4R7US-UR8UR:UR- S-UR<UR- S-URSSSSSS SSURS -S9nUUR?S5- [R@"URCSSS9S-5- nUREU5 GM [SU05nURUUUUURFUSS 9nUSnURIS5nURSURSURF-- nUSS2SU2SS24RKU UURF-UR8URF-5nUbJUSS2SU24RKU UURF-URF5R-SS!9RLn[UU UUS".US#9$s sn f)$a Args: audio (`np.ndarray`, `torch.Tensor`, `list[np.ndarray]`, `list[torch.Tensor]`): Numpy array or torch tensor with shape (num_channels, sequence_length). A list of such arrays or tensors can also be provided for a batch of inputs. 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). max_length (`int`, *optional*): Maximum length of the returned list and optionally padding length (see above). truncation (`bool`): Activates truncation to cut input sequences longer than *max_length* to *max_length*. 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 sample rate at which the `audio` input was sampled. It is strongly recommended to pass `sampling_rate` at the forward call to prevent silent errors. device (`str`, *optional*, defaults to `"cpu"`): Device for PyTorch tensors during mel-filter bank feature extraction. kwargs (*optional*): Remaining dictionary of keyword arguments that will be passed to the tokenizer or the feature extractor. Nz3The model corresponding to this feature extractor: z& was trained using a sampling rate of zD. 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.rz6Expected input shape (channels, length) but got shape )rrr)valuerpt)r3r4r2return_attention_maskpad_to_multiple_ofr5attention_maskriipoveyg ףp= ?TF) r)r*r+sample_frequency window_typepreemphasis_coefficientremove_dc_offset use_log_fbank use_energydither snip_edgeslow_freq high_freqr)unbiasedgHz>r)r2r3r4r=r<r5)dim)rrrr) tensor_type)'r ValueErrorloggerwarningr.__name__rndimshapelenFpadtorch as_tensorr&rr%poprangeintsumitemmintor compliancekaldifbankr)r*r+meansqrtvarappendr(getreshapevalues)r,rr2r3r4r5rr6r-example batch_sizea padded_inputsr padded_audio mel_featuresiorig_lenper_sample_len valid_lenwaveformfeaturesencoded_inputs padded_melaudio_spectrogramspectrogram_masktrimmed_framess r/__call__ Xcodec2FeatureExtractor.__call__UsZZ  $ 2 22 I$P**+,**+9]O1F3 NNVW[WeWeWnWnVop\\  #5)G||a #YZaZgZgYh!ijjZ HMMu!uq)6=uM4488 '5) *!!")#9 %(()9: $W-aqj9  z"A,>r,BCI#Aq*9*$45HuuX1(R'S[^_H{{6*H!,,2288E"!..!..1C1CCdJ ,,t/A/AADH!%!3!3#(,!%" ,,19H !8==#33uzz(,,q[_,B`cgBg7hhH    )1#2&'7&FGXX !!#{{") ''78%>>*:;*0037H7N7Nq7QTXT_T_7_`-a.!.CDLL $++5t7H7H4;;7V   ' O^O!34^t{{%BDKKP  , ,"3'7   '  ENs84Pc[R"UR5nURRUS'UR SS5 U$)Nfeature_extractor_typer&)copydeepcopy__dict__r.rRrZ)r,outputs r/to_dictXcodec2FeatureExtractor.to_dicts=t}}-+/>>+B+B'( ,d3 r1)r&r*r+r%r)r()r i>g?i@)TNFNNcpu)rR __module__ __qualname____firstlineno____doc__r'r$rboolstrr r\r rr|dictrr__static_attributes__ __classcell__)r.s@r/rr$s&b :15!% 26$(K K o-K $J K  K j(4/ K TzK K  K Zc3hr1r)rtypingr audio_utilsrr!feature_extraction_sequence_utilsrfeature_extraction_utilsrutilsr r r utils.import_utilsr r rrXtorch.nn.functionalnn functionalrVr get_loggerrRrPr__all__r"r1r/rs 9I499WW##   H % ?#A6A$AH % %r1