`i{dZddlmZmZddlZddlmZddlm Z ddl m Z m Z m Z e jeZGdd eZd gZdS) zFeature extractor class for DAC)OptionalUnionN)SequenceFeatureExtractor) BatchFeature)PaddingStrategy TensorTypeloggingc,eZdZdZddgZ dded ed ed effd Z ddee j e ee e j e e efde ee eefde e de ede eeefd e edefdZxZS)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_values n_quantizers> feature_size sampling_rate padding_value hop_lengthc Ptjd|||d|||_dS)N)rrr)super__init__r)selfrrrrkwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/dac/feature_extraction_dac.pyrzDacFeatureExtractor.__init__1s8 wl-_lwwpvwww$NF raw_audiopadding truncation max_lengthreturn_tensorsreturnc |2||jkr&td|d|jd|jd|d n(td|jjd|r|rtd |d }t t|ttfo,t|d tj ttf}|r d |D}n|s;t|tj s!tj |tj }n^t|tj rD|jtjtjur|tj }|stj |jg}t%|D]u\}} | jdkrtd| j|jdkr)| jdkrtd| jdd|jdkrtdvt-d|i} || |||||j} |r| d| d<|r#| jddtjddf| _g} | dD]/} |jdkr| d} | | j0| | d<|| |} | 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.TrcXg|]'}tj|tjj(S)dtype)npasarrayfloat32T).0audios r z0DacFeatureExtractor.__call__..~s,VVV5E<<<>VVVrr)z6Expected input shape (channels, length) but got shape rz$Expected mono audio but example has z channelsz$Stereo audio isn't supported for nowr )r#r"r!return_attention_maskpad_to_multiple_ofattention_mask padding_mask).N)r ValueErrorloggerwarningr__name__bool isinstancelisttupler+ndarrayr,r-r*float64astyper. enumeratendimshaperrpadrpopr newaxisappendconvert_to_tensors) rr r!r"r#r$r is_batchedidxexampler padded_inputss r__call__zDacFeatureExtractor.__call__<sT  $ 222 F$FF*FF*FF5BFFF3 NN\W[WeWn\\\     z `aa a _G y4- 0 0 jj1PRPZ\acgOh6i6i    5VVIVVVII 5Jy"*$E$E 5 9BJ???II  2: . . 59?bhrzFZFZ3Z3Z!((44I 2I..01I&i00 I ILC|a !iZaZg!i!ijjj A%%',!*;*; !d VXHY!d!d!deee A%% !GHHH&$^Y$?@@  !!")# !    P,9,=,=>N,O,OM. )  V)6)CAAArzSTSTSTDT)UM & $((88 + +G A%%!),    * * * *(4 n%  %)<<^LLMr)rrrr)NFNNN)r; __module__ __qualname____doc__model_input_namesintfloatrrr+r@r>rr<strrr rrO __classcell__)rs@rr r s\"(8"" % % % % %  % % % % % %@D%*$(;?'+ooT%[$rz2BDeDUUVo%c? :;<oTN o SM o !sJ!78 o }o oooooooorr )rRtypingrrnumpyr+!feature_extraction_sequence_utilsrfeature_extraction_utilsrutilsrr r get_loggerr;r9r __all__rrrr_s&%""""""""IIIIII4444449999999999  H % %NNNNN2NNNb ! !r