+ j*^RIt^RIHt^RIHtHt^RIHt^RIH t ^RI H t H t H t ^RIHtHtHt]!4'd^RIt^RIHuHt]!4'd^RIt] P0!]4t]!R R7!R R ]44tR .tR#) N)Any) AudioInputmake_list_of_audio)SequenceFeatureExtractor) BatchFeature)PaddingStrategy TensorTypelogging)is_torch_availableis_torchaudio_availablerequires)backendscjaa]tRt^$toRt.ROtR V3RlltR V3RlRlltV3RlRltRt Vt V;t #) Xcodec2FeatureExtractora 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. c <\SV`!R RVRVRV/VBW@n\^VRR7VnRR.VPn^Vn^PVnRVn^Vn R#) feature_size sampling_rate padding_value)rrraudio padding_maskiN) super__init__ hop_lengthracoustic_encoder_paddermodel_input_namesstride num_mel_bins frame_length frame_shift)selfrrrrkwargs __class__s&&&&&,w/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/xcodec2/feature_extraction_xcodec2.pyr Xcodec2FeatureExtractor.__init__;sz wlw-w_lwpvw%'?'( $ ;B>9R$$6 c<V^8dQhRS[RS[S[,S[,RS[R,RS[RS[S[,R,RS[R,RS[R S[/#) rpadding max_lengthN truncationreturn_tensorsrdevicereturn)rboolstrrintr r)format __classdict__s"r% __annotate__$Xcodec2FeatureExtractor.__annotate__UsK K K o-K $J K  K j(4/ K TzK K  K r'c > Ve>W`P8wd-\RV RVP RVP RV R2 4hM-\PRVPP R24\ V4pVF,p V P^8gK\R V P 24h \V4p VU u.uF0p \P!\P!V 4R R R 7NK2 pp VPP\R V/4VVVVVP R R7p V P#R4p V R ,R!,p.p\%V 4EFpV e/\'V V,P)4P+44MVPR",pVVP ,^, VP ,VP ,p\-VVPR",4pVVRRV13,p\P!VVP ^,VP ^,3R R 7pVP/V4p\0P2P4P7VR#,VP8VP:VP, R,VP<VP, R,VPRRRRRR R^VP^,R7pVVP?^4, \P@!VPC^RR7R,4, pVPEV4EK \RV/4pVPVVVVVPFVR R7pVR,pVPIR4pVP^,VP^,VPF,, pVRRV1R3,PKV VVPF,VP8VPF,4pVeTVRRV13,PKV VVPF,VPF4P-R"R7PLp\RVRV RVRV/VR7#uup i)$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.z6Expected input shape (channels, length) but got shape r)valuerpt)r+r,r*return_attention_maskpad_to_multiple_ofr-attention_maskNNNipoveyg ףp= ?TF) rr r!sample_frequency window_typepreemphasis_coefficientremove_dc_offset use_log_fbank use_energydither snip_edgeslow_freq high_freq)unbiasedgHz>input_features)r*r+r,r<r;r-)dim input_valuesrinput_features_mask) tensor_type)r)r>Nr>i)'r ValueErrorloggerwarningr$__name__rndimshapelenFpadtorch as_tensorrrrpopranger2sumitemminto torchaudio compliancekaldifbankrr r!meansqrtvarappendrgetreshapevalues)r"rr*r+r,r-rr.r#example batch_sizea padded_inputsr padded_audio mel_featuresiorig_lenper_sample_len valid_lenwaveformfeaturesencoded_inputs padded_melaudio_spectrogramspectrogram_masktrimmed_framess&&&&&&&&, r%__call__ Xcodec2FeatureExtractor.__call__Us^Z  $ 2 22 I$P**+,**+9]O1F3 NNVW[WeWeWnWnVop\\  #5)G||a #YZaZgZgYh!ijjZ HMMu!uq)6=uM4488 '5) *!!")#9 %(()9: $W-j9  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 $++5t7H7H4;;7V   ' O^O!34^t{{%BDKKP    "3%'7   '  ENs;6Rc6<V^8dQhRS[S[S[3,/#)r)r/)dictr1r)r3r4s"r%r5r6sc3hr'c\P!VP4pVPPVR&VP RR4V#)feature_extractor_typerN)copydeepcopy__dict__r$rUr])r"outputs& r%to_dictXcodec2FeatureExtractor.to_dicts=t}}-+/>>+B+B'( ,d3 r')rr r!rrr)rKrMrrN)Pi>g?i@)TNFNNcpu) rU __module__ __qualname____firstlineno____doc__rrrr__static_attributes____classdictcell__ __classcell__)r$r4s@@r%rr$s4&b4K K Zr'r)rc)rtypingr audio_utilsrr!feature_extraction_sequence_utilsrfeature_extraction_utilsrutilsrr r utils.import_utilsr r r r[torch.nn.functionalnn functionalrYrc get_loggerrUrSr__all__rr'r%rs 9I499WW##   H % ?#A6A$AH % %r'