`iLdZddlZddlmZddlmZGddeZdgZdS)z$ Speech processor class for M-CTC-T N)contextmanager)ProcessorMixincReZdZdZdZdZfdZdZdZdZ e dZ xZ S) MCTCTProcessora[ Constructs a MCTCT processor which wraps a MCTCT feature extractor and a MCTCT tokenizer into a single processor. [`MCTCTProcessor`] offers all the functionalities of [`MCTCTFeatureExtractor`] and [`AutoTokenizer`]. See the [`~MCTCTProcessor.__call__`] and [`~MCTCTProcessor.decode`] for more information. Args: feature_extractor (`MCTCTFeatureExtractor`): An instance of [`MCTCTFeatureExtractor`]. The feature extractor is a required input. tokenizer (`AutoTokenizer`): An instance of [`AutoTokenizer`]. The tokenizer is a required input. MCTCTFeatureExtractor AutoTokenizercrt|||j|_d|_dS)NF)super__init__feature_extractorcurrent_processor_in_target_context_manager)selfr tokenizer __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/deprecated/mctct/processing_mctct.pyr zMCTCTProcessor.__init__*s7 *I666!%!7*/'''c|jr |j|i|Sd|vr*tjd|d}n|dd}|dd}|dd}t |dkr|d}|dd}||t d ||j|g|Rd|i|}||j|fi|}||S||S|d |d <|S) a When used in normal mode, this method forwards all its arguments to MCTCTFeatureExtractor's [`~MCTCTFeatureExtractor.__call__`] and returns its output. If used in the context [`~MCTCTProcessor.as_target_processor`] this method forwards all its arguments to AutoTokenizer's [`~AutoTokenizer.__call__`]. Please refer to the docstring of the above two methods for more information. raw_speechzLUsing `raw_speech` as a keyword argument is deprecated. Use `audio` instead.audioN sampling_ratetextrzAYou need to specify either an `audio` or `text` input to process. input_idslabels) rrwarningswarnpoplen ValueErrorr r)rargskwargsrrrinputs encodingss r__call__zMCTCTProcessor.__call__/sB  * ;)4)4:6:: : 6 ! ! Mh i i iJJ|,,EEJJw--E ?D99 zz&$'' t99q==GE8D =T\`aa a  +T+E`D``` `Y_``F  &t66v66I <M ] (5F8 MrcZ|jr|jj|i|S|dd}|dd}t |dkr|d}|dd}||jj|g|Ri|}||jj|fi|}||S||S|d|d<|S)a When used in normal mode, this method forwards all its arguments to MCTCTFeatureExtractor's [`~MCTCTFeatureExtractor.pad`] and returns its output. If used in the context [`~MCTCTProcessor.as_target_processor`] this method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.pad`]. Please refer to the docstring of the above two methods for more information. input_featuresNrrrr)rrpadrr r r)rr"r#r(rs rr)zMCTCTProcessor.padUs  * ?-4)-t>v>> >$4d;;Hd++ t99q==!!WN8D  %7T37XXXXQWXXN  'T^'99&99F >! !  #M'-k':N8 $! !rc&|jj|i|S)z This method forwards all its arguments to AutoTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecode)rr"r#s rr+zMCTCTProcessor.decodess %t~$d5f555rc#Ktjdd|_|j|_dV|j|_d|_dS)z Temporarily sets the tokenizer for processing the input. Useful for encoding the labels when fine-tuning MCTCT. z`as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.TNF)rrrrrr )rs ras_target_processorz"MCTCTProcessor.as_target_processorzsW   8   +/'!% !%!7*/'''r) __name__ __module__ __qualname____doc__feature_extractor_classtokenizer_classr r&r)r+rr- __classcell__)rs@rrrs  6%O00000 $$$L"""<666 0 0^ 0 0 0 0 0rr)r1r contextlibrprocessing_utilsrr__all__rrr9s%%%%%%//////o0o0o0o0o0^o0o0o0d  r