cCi`YSrSSKJrJrJr SSKrSSKJrJ r J r J r SSK J r SSKJr SSKJrJrJr \R("\5r"S S \ 5rS /rg) z)Feature extractor class for UnivNetModel.)AnyOptionalUnionN)mel_filter_bankoptimal_fft_length spectrogramwindow_function)SequenceFeatureExtractor) BatchFeature)PaddingStrategy TensorTypeloggingc)^\rSrSrSr/SQrS/S\S\S\S\S\S \S \S \ S \ \S \S\S\ \S\S\S\S\S\S\S\S\4(U4Sjjjr Sr Sr S\RS\R4SjrS0S\S\ \R"R$S\R4S jjrS0S\\R4S!jjrS1S"\\R\\\\R\\\4S\ \S#\\\ \4S$\ \S%\S&\ \S'\S\ \R"R$S(\S)\ \S\ \ S*\ \S+\ \\ \4S\4S,jjrS\\ \44U4S-jjrS.rU=r$)2UnivNetFeatureExtractora Constructs a UnivNet feature extractor. This class extracts log-mel-filter bank features from raw speech using the short time Fourier Transform (STFT). The STFT implementation follows that of TacoTron 2 and Hifi-GAN. 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. Args: feature_size (`int`, *optional*, defaults to 1): The feature dimension of the extracted features. sampling_rate (`int`, *optional*, defaults to 24000): The sampling rate at which the audio files should be digitalized expressed in hertz (Hz). padding_value (`float`, *optional*, defaults to 0.0): The value to pad with when applying the padding strategy defined by the `padding` argument to [`UnivNetFeatureExtractor.__call__`]. Should correspond to audio silence. The `pad_end` argument to `__call__` will also use this padding value. do_normalize (`bool`, *optional*, defaults to `False`): Whether to perform Tacotron 2 normalization on the input. Normalizing can help to significantly improve the performance for some models. num_mel_bins (`int`, *optional*, defaults to 100): The number of mel-frequency bins in the extracted spectrogram features. This should match `UnivNetModel.config.num_mel_bins`. hop_length (`int`, *optional*, defaults to 256): The direct number of samples between sliding windows. Otherwise referred to as "shift" in many papers. Note that this is different from other audio feature extractors such as [`SpeechT5FeatureExtractor`] which take the `hop_length` in ms. win_length (`int`, *optional*, defaults to 1024): The direct number of samples for each sliding window. Note that this is different from other audio feature extractors such as [`SpeechT5FeatureExtractor`] which take the `win_length` in ms. win_function (`str`, *optional*, defaults to `"hann_window"`): Name for the window function used for windowing, must be accessible via `torch.{win_function}` filter_length (`int`, *optional*, defaults to 1024): The number of FFT components to use. If `None`, this is determined using `transformers.audio_utils.optimal_fft_length`. max_length_s (`int`, *optional*, defaults to 10): The maximum input length of the model in seconds. This is used to pad the audio. fmin (`float`, *optional*, defaults to 0.0): Minimum mel frequency in Hz. fmax (`float`, *optional*): Maximum mel frequency in Hz. If not set, defaults to `sampling_rate / 2`. mel_floor (`float`, *optional*, defaults to 1e-09): Minimum value of mel frequency banks. Note that the way [`UnivNetFeatureExtractor`] uses `mel_floor` is different than in [`transformers.audio_utils.spectrogram`]. center (`bool`, *optional*, defaults to `False`): Whether to pad the waveform so that frame `t` is centered around time `t * hop_length`. If `False`, frame `t` will start at time `t * hop_length`. compression_factor (`float`, *optional*, defaults to 1.0): The multiplicative compression factor for dynamic range compression during spectral normalization. compression_clip_val (`float`, *optional*, defaults to 1e-05): The clip value applied to the waveform before applying dynamic range compression during spectral normalization. normalize_min (`float`, *optional*, defaults to -11.512925148010254): The min value used for Tacotron 2-style linear normalization. The default is the original value from the Tacotron 2 implementation. normalize_max (`float`, *optional*, defaults to 2.3143386840820312): The max value used for Tacotron 2-style linear normalization. The default is the original value from the Tacotron 2 implementation. model_in_channels (`int`, *optional*, defaults to 64): The number of input channels to the [`UnivNetModel`] model. This should match `UnivNetModel.config.model_in_channels`. pad_end_length (`int`, *optional*, defaults to 10): If padding the end of each waveform, the number of spectrogram frames worth of samples to append. The number of appended samples will be `pad_end_length * hop_length`. return_attention_mask (`bool`, *optional*, defaults to `True`): Whether or not [`~UnivNetFeatureExtractor.__call__`] should return `attention_mask`. )input_featuresnoise_sequence padding_mask feature_size sampling_rate padding_value do_normalize num_mel_bins hop_length win_length win_function filter_length max_length_sfminfmax mel_floorcentercompression_factorcompression_clip_val normalize_min normalize_maxmodel_in_channelspad_end_lengthc >[TU]"SUUUUS.UD6 X@lXPlX`lXplXlXlXlU c[U5S- n Xl Xl Xl X-Ul URc[UR 5UlOURUlURS-S-Ul[#UR UR SS9Ul['UR URURURUR(SSS9UlXlXlUUlUUlUUlUUlUUlg) N)rrrreturn_attention_maskT) window_lengthnameperiodicslaney)num_frequency_binsnum_mel_filters min_frequency max_frequencyrnorm mel_scale)super__init__rrrrrrr floatr!r"rnum_max_samplesrn_fftn_freqsr windowrr mel_filtersr#r$r%r&r'r(r))selfrrrrrrrrrrr r!r"r#r$r%r&r'r(r)r+kwargs __class__s p/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/univnet/feature_extraction_univnet.pyr: UnivNetFeatureExtractor.__init__esL2  %''"7    )($$(* <'!+D "(+;    %+DOO= 7.5` (Volta), or on TPUs which benefit from having sequence lengths be a multiple of 128. return_noise (`bool`, *optional*, defaults to `True`): Whether to generate and return a noise waveform for use in [`UnivNetModel.forward`]. generator (`numpy.random.Generator`, *optional*, defaults to `None`): An optional `numpy.random.Generator` random number generator to use when generating noise. pad_end (`bool`, *optional*, defaults to `False`): Whether to pad the end of each waveform with silence. This can help reduce artifacts at the end of the generated audio sample; see https://github.com/seungwonpark/melgan/issues/8 for more details. This padding will be done before the padding strategy specified in `padding` is performed. pad_length (`int`, *optional*, defaults to `None`): If padding the end of each waveform, the length of the padding in spectrogram frames. If not set, this will default to `self.config.pad_end_length`. do_normalize (`bool`, *optional*): Whether to perform Tacotron 2 normalization on the input. Normalizing can help to significantly improve the performance for some models. If not set, this will default to `self.config.do_normalize`. return_attention_mask (`bool`, *optional*): Whether to return the attention mask. If left to the default, will return the attention mask according to the specific feature_extractor's default. [What are attention masks?](../glossary#attention-mask) 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.np.array` objects. - `'np'`: Return Numpy `np.ndarray` objects. z3The model corresponding to this feature extractor: z& was trained using a sampling rate of zI. Please make sure that the provided `raw_speech` 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.r-r,z2Only mono-channel audio is supported for input to rrk)constant_valuesr)rrrrr+attention_maskrr)rr ValueErrorrC__name__loggerwarning isinstancerYndarraylenshapelisttupleasarrayrprlfloat64astyper)rZrrr r<getreint32rsrJconvert_to_tensors)rArrrrrrrrirrrr+ris_batched_numpy is_batchedspeechrObatched_speech padded_inputsrmel_spectrogramsmelrarrayr rrs rD__call__ UnivNetFeatureExtractor.__call__s2X(4'?|TEVEV  $ 2 22 I$..JaJaIbc))-););(<=))-););(ZJXJJz2::$F$FJbjjAJ  BJJ / /J4D4DQSQ[Q[H\4\#**2::6J**ZrzzBCJ '1'=4CVCVJ!+ *Hx!Z//%A!BTXTfTfg *  &'7&DE %/%;zAUAU!1"7 ! '**+;<KYZ>xD00:>Z nQ' . .]m/n]mVY 3bjj0Q]m/nN+ ,Rb/cRb3 2::0FRb/cN+ ,'**+;<  %]k-l]kTYbjjbhh.O]k-lN> * $22B#C#CK##K$5$5a$8)D#C 05N+ , ?MN^?_0?_ {+?_0N+ ,  %+>>~NNyY([0o/c .m0s0-Q/8Q4Q9:-Q>2)R9-R:)R 8RcP>[TU]5n/SQnUH nX1;dM X M U$)N)r?r@r=r>r<)r9to_dict)rAoutputnamesr/rCs rDrUnivNetFeatureExtractor.to_dicts2"QD~L rF)r#r%r$rrr!r rrr@r"r(r=r>r'r&r<rr)rrr?)r-i]Fd hann_windowr rNg& .>Fg?gh㈵>g 'gă@@rT)N) NTNTNTNFNNNN) r __module__ __qualname____firstlineno____doc__model_input_namesr[r;boolstrrr:rJrMrYrrerm Generatorrsrrrr rr rdictrr__static_attributes__ __classcell__)rCs@rDrrsCJM""")'+ $$'&*21!# "-J-J-J- J-  J-  J-J-J-J- }J-J-J-uoJ-J-J- "!J-"$#J-$%J-&'J-()J-*+J-J-Xhh.% .%rzz.%f48BII//0  @RZZ@P4(,59$(,0!37$(&*04;?_"**d5k4 3CT$u+EVVW_ }_tS/12 _ SM _  _%SM__BII//0__SM_sm_ (~_!sJ!78_ _B c3h  rFr)rtypingrrrr{rY audio_utilsrrr r !feature_extraction_sequence_utilsr feature_extraction_utilsr utilsr rr get_loggerrrr__all__r8rFrDrsQ0''\\I499   H %k6k\ % %rF