o Zh@spdZddlmZmZmZddlZddlmZddl m Z ddl m Z m Z mZeeZGdd d eZd gZdS) zFeature extractor class for DAC)ListOptionalUnionN)SequenceFeatureExtractor) BatchFeature)PaddingStrategy TensorTypeloggingcseZdZdZddgZ    dded ed ed effd d Z     ddee j e ee e j e e efde ee eefde e de ede eeefd e edefddZZS)DacFeatureExtractora> Constructs an Dac 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. Args: feature_size (`int`, *optional*, defaults to 1): The feature dimension of the extracted features. Use 1 for mono, 2 for stereo. sampling_rate (`int`, *optional*, defaults to 16000): The sampling rate at which the audio waveform should be digitalized, expressed in hertz (Hz). padding_value (`float`, *optional*, defaults to 0.0): The value that is used for padding. hop_length (`int`, *optional*, defaults to 512): Overlap length between successive windows. input_valuesZ n_quantizers> feature_size sampling_rate padding_value hop_lengthc s$tjd|||d|||_dS)N)rrr)super__init__r)selfrrrrkwargs __class__r]/var/www/auris/lib/python3.10/site-packages/transformers/models/dac/feature_extraction_dac.pyr1s zDacFeatureExtractor.__init__NF raw_audiopadding truncation max_lengthreturn_tensorsreturnc Cs|dur||jkrtd|d|jd|jd|d n td|jjd|r0|r0td |dur6d }tt|tt foHt|d t j t tf}|rTd d |D}n&|set|t j set j |t j d}nt|t j rz|jt t jurz|t j }|st |jg}t|D]/\}} | jdkrtd| j|jdkr| jdkrtd| jdd|jdkrtdqtd|i} |j| |||d|jd} |r| jddt jddf| _g} | dD]} |jdkr| d} | | jq| | d<|dur| |} | S)a Main method to featurize and prepare for the model one or several sequence(s). Args: raw_audio (`np.ndarray`, `List[float]`, `List[np.ndarray]`, `List[List[float]]`): The sequence or batch of sequences to be processed. 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. The numpy array must be of shape `(num_samples,)` for mono audio (`feature_size = 1`), or `(2, num_samples)` for stereo audio (`feature_size = 2`). 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). truncation (`bool`, *optional*, defaults to `False`): Activates truncation to cut input sequences longer than `max_length` to `max_length`. max_length (`int`, *optional*): Maximum length of the returned list and optionally padding length (see above). return_tensors (`str` or [`~utils.TensorType`], *optional*, default to 'pt'): 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 sampling rate at which the `audio` input was sampled. It is strongly recommended to pass `sampling_rate` at the forward call to prevent silent errors. Nz3The model corresponding to this feature extractor: z& was trained using a sampling rate of zB. 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.zABoth padding and truncation were set. Make sure you only set one.TrcSsg|] }tj|tjdjqS)dtype)npasarrayfloat32T).0Zaudiorrr ~sz0DacFeatureExtractor.__call__..r$z6Expected input shape (channels, length) but got shape r z$Expected mono audio but example has z channelsz$Stereo audio isn't supported for nowr F)r rrZreturn_attention_maskZpad_to_multiple_of).N)r ValueErrorloggerwarningr__name__bool isinstancelisttupler&ndarrayr'r(r%Zfloat64Zastyper) enumeratendimshaperrpadrr ZnewaxispopappendZconvert_to_tensors) rrrrr r!rZ is_batchedidxZexampler Z padded_inputsrrr__call__<st* "       zDacFeatureExtractor.__call__)r rrr)NFNNN)r1 __module__ __qualname____doc__Zmodel_input_namesintfloatrrr&r6rrr2strrr rr> __classcell__rrrrr sH"r )rAtypingrrrnumpyr&Z!feature_extraction_sequence_utilsrZfeature_extraction_utilsrutilsrr r Z get_loggerr1r/r __all__rrrrs