+ jc*Rt^RIt^RIHtHtHt^RIHt^RI H t ^RI H t H t ] P!]4t!RR]4tR.tR#)z" Feature extractor class for CLVP N)mel_filter_bank spectrogramwindow_function)SequenceFeatureExtractor) BatchFeature) TensorTypeloggingcjaa]tRt^toRtRR.tR V3RlltV3RlRltR V3RlRlltR t Vt V;t #) ClvpFeatureExtractora Constructs a CLVP 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. This class extracts log-mel-spectrogram features from raw speech using a custom numpy implementation of the `Short Time Fourier Transform` which should match pytorch's `torch.stft` equivalent. Args: feature_size (`int`, *optional*, defaults to 80): The feature dimension of the extracted features. sampling_rate (`int`, *optional*, defaults to 22050): The sampling rate at which the audio files should be digitalized expressed in hertz (Hz). default_audio_length (`int`, *optional*, defaults to 6): The default length of raw audio in seconds. If `max_length` is not set during `__call__` then it will automatically be set to default_audio_length * `self.sampling_rate`. hop_length (`int`, *optional*, defaults to 256): Length of the overlapping windows for the STFT used to obtain the Mel Frequency coefficients. chunk_length (`int`, *optional*, defaults to 30): The maximum number of chunks of `sampling_rate` samples used to trim and pad longer or shorter audio sequences. n_fft (`int`, *optional*, defaults to 1024): Size of the Fourier transform. padding_value (`float`, *optional*, defaults to 0.0): Padding value used to pad the audio. Should correspond to silences. mel_norms (`list` of length `feature_size`, *optional*): If `mel_norms` is provided then it will be used to normalize the log-mel spectrograms along each mel-filter. return_attention_mask (`bool`, *optional*, defaults to `False`): Whether to return the attention mask. If left to the default, it will return the attention mask. [What are attention masks?](../glossary#attention-mask) input_featuresattention_maskc <\S V`!R RVRVRVRV /V BW`nW@nWPnWR,VnVP V,VnW nW0nWn \^V^,,VRRVRRR7Vn R #) feature_size sampling_rate padding_valuereturn_attention_maskg@@slaneyhtk)num_frequency_binsnum_mel_filters min_frequency max_frequencyrnorm mel_scaleN) super__init__n_fft hop_length chunk_length n_samples nb_max_framesrdefault_audio_length mel_normsr mel_filters) selfrrr#rr rrr$rkwargs __class__s &&&&&&&&&&,q/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/clvp/feature_extraction_clvp.pyrClvpFeatureExtractor.__init__Ds  % ' ( #8     $(%5!^^z9*$8!"* EQJ/( ' cN<V^8dQhRS[PRS[P/#)waveformreturn)npndarray)format __classdict__s"r) __annotate__!ClvpFeatureExtractor.__annotate__js#2::"**r+c  `\V\VPR4VPVPRVPRR7p\ P !\ P!VRRR74pVPe/V\ P!VP4R,, pV#)z This method first computes the log-mel spectrogram of the provided audio then applies normalization along the each mel-filterbank, if `mel_norms` is provided. hanng@N) frame_lengthrpowerr%log_melgh㈵>)a_mina_max):NNNN) rrrrr%r0logclipr$array)r&r.log_specs&& r)_np_extract_fbank_features/ClvpFeatureExtractor._np_extract_fbank_featuresjs   DJJ /(( 66"''($dCD >> %"((4>>":7"CCHr+cL<V^8dQhRS[PS[S[,,S[S[P,,S[S[S[,,,RS[R,RS[RS[R,RS[S[,R,RS[R,RS[R,R S[R,R S[/ #) r- raw_speechrN truncationpad_to_multiple_ofreturn_tensorsrpadding max_lengthr/) r0r1listfloatintboolstrrr)r2r3s"r)r4r5sj@j@JJe,tBJJ/??$tE{BSSj@Tzj@ j@  $J j@ j(4/ j@ $d{j@tj@$Jj@ j@r+c VeRW P8wdA\RVPP RVP RVP RV R2 4hM-\P RVPP R24\ V\P4;'d\VP4^8p V 'd)\VP4^8d\RV 24hT ;'gK\ V\\34;'d-\ V^,\P\\34p V 'dBVU u.uF4p \P!V .\PR 7PNK6 pp MV 'gH\ V\P4'g(\P!V\PR 7pMq\ V\P4'dRVP \P !\P"4Jd VP%\P4pV 'g#\P!V.4P.p\'R V/4p VfVP(VP,MTpVP+V VVVVVR 7pVP-R 4P/^^^4pV^,Uu.uF1pVP1V4P%\P4NK3 pp\ V^,\4'd+VUu.uFp\P!V4NK upVR &MWR &VP3V4#uup iuupiuupi) a `ClvpFeatureExtractor` is used to extract various voice specific properties such as the pitch and tone of the voice, speaking speed, and even speaking defects like a lisp or stuttering from a sample voice or `raw_speech`. First the voice is padded or truncated in a way such that it becomes a waveform of `self.default_audio_length` seconds long and then the log-mel spectrogram is extracted from it. Args: raw_speech (`np.ndarray`, `list[float]`, `list[np.ndarray]`, `list[list[float]]`): The sequence or batch of sequences to be padded. 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. Must be mono channel audio, not stereo, i.e. single float per timestep. sampling_rate (`int`, *optional*): The sampling rate at which the `raw_speech` input was sampled. It is strongly recommended to pass `sampling_rate` at the forward call to prevent silent errors and allow automatic speech recognition pipeline. truncation (`bool`, *optional*, default to `True`): Activates truncation to cut input sequences longer than *max_length* to *max_length*. pad_to_multiple_of (`int`, *optional*): If set will pad the sequence to a multiple of the provided value. This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability `>= 7.5` (Volta), or on TPUs which benefit from having sequence lengths be a multiple of 128. return_attention_mask (`bool`, *optional*, defaults to `True`): Whether to return the attention mask. If left to the default, it will return the attention mask. [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: - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return Numpy `np.ndarray` objects. padding_value (`float`, *optional*, defaults to 0.0): The value that is used to fill the padding values / vectors. max_length (`int`, *optional*): The maximum input length of the inputs. 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.z2Only mono-channel audio is supported for input to )dtyper )rHrIrErFr)r ValueErrorr(__name__loggerwarning isinstancer0r1lenshaperJtupleasarrayfloat32TrQfloat64astyperr#padget transposerAconvert_to_tensors)r&rDrrErFrGrrHrIr'is_batched_numpy is_batchedspeechbatched_speech padded_inputsr r.features&&&&&&&&&, r)__call__ClvpFeatureExtractor.__call__s d  $ 2 22 I$..JaJaIbc))-););(<=))-););(!F*+;<$ L,j@j@j@r+r )rrnumpyr0 audio_utilsrrr!feature_extraction_sequence_utilsrfeature_extraction_utilsrutilsrr get_loggerrSrTr __all__rr+r)r~sLHHI4(   H %L@3L@^ " "r+