sg*dZddlmZmZmZddlZddlmZm Z m Z ddl m Z ddl mZddlmZmZej$eZGd d e Zy) z" Feature extractor class for CLVP )ListOptionalUnionN)mel_filter_bank spectrogramwindow_function)SequenceFeatureExtractor) BatchFeature) TensorTypeloggingc.eZdZdZddgZ dfd ZdejdejfdZ dd e eje e e eje e e fd e ed ed e ed e e eefde ede ede edefdZxZS)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 overlaping windows for the STFT used to obtain the Mel Frequency coefficients. chunk_length (`int`, *optional*, defaults to 30): The maximum number of chuncks 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 t |d |||| d| ||_||_||_||z|_|j |z|_||_||_||_ td|dzz|dd|dd|_ y) N) feature_size sampling_rate padding_valuereturn_attention_maskg@@slaneyhtk)num_frequency_binsnum_mel_filters min_frequency max_frequencyrnorm mel_scale) super__init__n_fft hop_length chunk_length n_samples nb_max_framesrdefault_audio_length mel_normsr mel_filters) selfrrr*r&r'r%rr+rkwargs __class__s c/var/www/html/venv/lib/python3.12/site-packages/transformers/models/clvp/feature_extraction_clvp.pyr$zClvpFeatureExtractor.__init__Gs  %''"7     $(% 5!^^z9*$8!"* EQJ/( ' waveformreturnc Nt|t|jd|j|jd|jd}t j t j|dd}|j)|t j|jdddfz }|S)z This method first computes the log-mel spectrogram of the provided audio then applies normalization along the each mel-filterbank, if `mel_norms` is provided. hanng@N) frame_lengthr&powerr,log_melgh㈵>)a_mina_max) rr r%r&r,nplogclipr+array)r-r2log_specs r0_np_extract_fbank_featuresz/ClvpFeatureExtractor._np_extract_fbank_featuresms   DJJ /(( 66"''($dCD >> %"((4>>":1d7"CCHr1 max_length raw_speechr truncationpad_to_multiple_ofreturn_tensorsrpaddingc (|O||jk7rUtd|jjd|jd|jd|d tj dt |tjxrt|jdkD} | r&t|jdkDrtd || xs@t |ttfxr(t |d tjttf} | r>|D cgc]2} tj| gtj j4}} n| s@t |tjs&tj|tj }nht |tjrN|j tj tj"ur|j%tj}| s!tj|gjg}t'd |i} ||j(|jzn|}|j+| ||||| }|j-d j/dd d}|d Dcgc]0}|j1|j%tj2}}t |d t2r'|Dcgc]}tj|c}|d <n||d <|j5|Scc} wcc}wcc}w)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: - `'tf'`: Return TensorFlow `tf.constant` objects. - `'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 .zIt is strongly recommended to pass the `sampling_rate` argument to this function. Failing to do so can result in silent errors that might be hard to debug.rrz2Only mono-channel audio is supported for input to r)dtyper)rFrArCrDr)r ValueErrorr/__name__loggerwarning isinstancer;ndarraylenshapelisttupleasarrayfloat32TrIfloat64astyper r*padget transposer@rconvert_to_tensors)r-rBrrCrDrErrFrAr.is_batched_numpy is_batchedspeechbatched_speech padded_inputsrr2features r0__call__zClvpFeatureExtractor.__call__sf  $ 2 22 I$..JaJaIbc))-););(<=))-););(5L  L) Pi"VirNF)NTNNTrAN)rK __module__ __qualname____doc__model_input_namesr$r;r>rOr@rrfloatrintboolstrr r rc __classcell__)r/s@r0rr!s'!F*+;<#$ L288 2(,,0;?04!-$(k@"**d5k4 3CT$u+EVVWk@ }k@ k@ %SM k@ !sJ!78 k@ (~k@#k@SMk@ k@r1r)rjtypingrrrnumpyr; audio_utilsrrr !feature_extraction_sequence_utilsr feature_extraction_utilsr utilsr r get_loggerrKrLrr"r1r0rxsI )(HHI4(   H %M@3M@r1