^j |dZddlZddlmZddlmZddlmZm Z m Z e je Z GddeZdgZy) zFeature extractor class for DiaN)SequenceFeatureExtractor) BatchFeature)PaddingStrategy TensorTypeloggingceZdZdZddgZ ddedededeffd Z dd eje eze ejze e ezd e e ze zd zd e d zd ed zde ezd zded zdefdZxZS)DiaFeatureExtractora> Constructs an Dia 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 :t|d|||d|||_y)N)r rr)super__init__r)selfr rrrkwargs __class__s y/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/dia/feature_extraction_dia.pyrzDiaFeatureExtractor.__init__.s' wl-_lwpvw$N raw_audiopadding truncation max_lengthreturn_tensorsreturnc |;||jk7rYtd|d|jd|jd|d tjd|jj d|r |r td|d }t t|ttfxr(t|d tjttf}|r=|Dcgc]1}tj|tj j3}}n|s@t|tjs&tj|tj }nht|tjrN|jtjtj ur|j#tj}|s tj|jg}t%|D]>\} } |j&d k(s| j(d k(s&tj*| d || <@t%|D]\} } | j(d kDrtd| j,|j&dk(r+| j(dk7rtd| j,d d|j&d k(sw| j(dk7std| j,d dt/d|i} |j&} d|_|j1| |||d |j2} | j5d| d<g} | j5dD]1} |j&dk(r| d} | j7| j3| | d<|| j9|} | |_| Scc}w)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: - `'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. z3The 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.Tr)dtypez6Expected input shape (channels, length) but got shape z$Expected mono audio but example has z channelsz&Expected stereo audio but example has r )rrrreturn_attention_maskpad_to_multiple_ofattention_mask padding_mask).N)r ValueErrorloggerwarningr__name__bool isinstancelisttuplenpndarrayasarrayfloat32Tr"float64astype enumerater ndimmeanshaperpadrpopappendconvert_to_tensors)rrrrrrr is_batchedaudioidxexampler original_feature_size padded_inputss r__call__zDiaFeatureExtractor.__call__9stR  $ 2 22 I$P**+,**+9]O1F NNVW[WeWeWnWnVop\\  z`a a _G y4- 0 jj1PRPZPZ\acgOh6i  LUV5E<>>VIVJy"**$E 9BJJ?I  2:: .9??bhhrzzFZ3Z!((4II.001I&i0 6LC  A%',,!*;!#"!5 # 6 &i0 hLC||a #YZaZgZgYh!ijj  A%',,!*; #G VXHYGZZc!dee  A%',,!*; #I'--XZJ[I\\e!fgg  h$^Y$?@ !% 1 1 !!"&# ! )6(9(9:J(K n% $((8 +G  A%!),    * + )5 n%  %)<<^LM2mWs 6N )r%i>gi)NFNNN)r- __module__ __qualname____doc__model_input_namesintfloatrr2r3r0r.strrrrrG __classcell__)rs@rr r s"(8"" % % % %  %8<"'!%26$(w::U +d2::.>>d5kARRwo-4w4K w $J w j(4/ wTzw wrr )rJnumpyr2!feature_extraction_sequence_utilsrfeature_extraction_utilsrutilsrrr get_loggerr-r+r __all__rrrrVsG&I499   H %V2Vr ! !r