o Zh&@spdZddlmZmZmZddlZddlmZddl m Z ddl m Z m Z mZeeZGdd d eZd gZdS) z$Feature extractor class for EnCodec.)ListOptionalUnionN)SequenceFeatureExtractor) BatchFeature)PaddingStrategy TensorTypeloggingcseZdZdZddgZ     dded ed ed eed eef fd d Ze deefddZ e deefddZ     dde e jeeee jeeefdee eeefdeedeedee eefd eedefddZZS)EncodecFeatureExtractora Constructs an EnCodec feature extractor. This feature extractor inherits from [`~feature_extraction_sequence_utils.SequenceFeatureExtractor`] which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. Instantiating a feature extractor with the defaults will yield a similar configuration to that of the [facebook/encodec_24khz](https://huggingface.co/facebook/encodec_24khz) architecture. Args: feature_size (`int`, *optional*, defaults to 1): The feature dimension of the extracted features. Use 1 for mono, 2 for stereo. sampling_rate (`int`, *optional*, defaults to 24000): The sampling rate at which the audio waveform should be digitalized expressed in hertz (Hz). padding_value (`float`, *optional*, defaults to 0.0): The value that is used to fill the padding values. chunk_length_s (`float`, *optional*): If defined the audio is pre-processed into chunks of lengths `chunk_length_s` and then encoded. overlap (`float`, *optional*): Defines the overlap between each chunk. It is used to compute the `chunk_stride` using the following formulae : `int((1.0 - self.overlap) * self.chunk_length)`. input_values padding_mask]N feature_size sampling_rate padding_valuechunk_length_soverlapc s*tjd|||d|||_||_dS)N)rrr)super__init__rr)selfrrrrrkwargs __class__re/var/www/auris/lib/python3.10/site-packages/transformers/models/encodec/feature_extraction_encodec.pyr7s  z EncodecFeatureExtractor.__init__returncCs|jdurdSt|j|jS)N)rintrrrrr chunk_lengthEs z$EncodecFeatureExtractor.chunk_lengthcCs2|jdus |jdur dStdtd|j|jS)Nrg?)rrmaxrr!r rrr chunk_strideMsz$EncodecFeatureExtractor.chunk_strideF raw_audiopadding truncation max_lengthreturn_tensorsc 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|jdkr| jddkrtd| jddqd} td|i} |jdur#|jdur#|dur#|rtdd|D}tt ||j} | d|j|j}n%|r!tdd|D}tt ||j} | d|j|j}d}n| } | dur<|j| ||||d} |r<| d| d<g} | dD]} |jdkrO| d} | | jqC| | d<|dure| !|} | 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*): 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 sz4EncodecFeatureExtractor.__call__..r*z6Expected input shape (channels, length) but got shape rz$Expected mono audio but example has z channelsz&Expected stereo audio but example has r cs|]}|jdVqdSrNshaper0arrayrrr z3EncodecFeatureExtractor.__call__..csr4r5r6r8rrrr:r;r')r'r&r%Zreturn_attention_maskZattention_maskr ).N)"r ValueErrorloggerwarningr__name__bool isinstancelisttupler,ndarrayr-r.r+Zfloat64Zastyper/ enumeratendimr7rrr#r!minrfloorr"ceilpadpopappendZconvert_to_tensors) rr$r%r&r'r(rZ is_batchedidxZexampleZ padded_inputsr Znb_steprrr__call__Ts* "   "    z EncodecFeatureExtractor.__call__)rrrNN)NFNNN)r? __module__ __qualname____doc__Zmodel_input_namesrfloatrrpropertyr!r#rr,rDrr@strrr rrN __classcell__rrrrr sV "r )rQtypingrrrnumpyr,Z!feature_extraction_sequence_utilsrZfeature_extraction_utilsrutilsrr r Z get_loggerr?r=r __all__rrrrs    5