U 9%e@sPdZddlZddlmZddlmZddlmZddlm Z Gd d d eZ dS) z% Speech processor class for Wav2Vec2 N)contextmanager)ProcessorMixin)Wav2Vec2FeatureExtractor)Wav2Vec2CTCTokenizercsdeZdZdZdZdZfddZefddZdd Z d d Z d d Z ddZ e ddZZS)Wav2Vec2Processora Constructs a Wav2Vec2 processor which wraps a Wav2Vec2 feature extractor and a Wav2Vec2 CTC tokenizer into a single processor. [`Wav2Vec2Processor`] offers all the functionalities of [`Wav2Vec2FeatureExtractor`] and [`PreTrainedTokenizer`]. See the docstring of [`~Wav2Vec2Processor.__call__`] and [`~Wav2Vec2Processor.decode`] for more information. Args: feature_extractor (`Wav2Vec2FeatureExtractor`): An instance of [`Wav2Vec2FeatureExtractor`]. The feature extractor is a required input. tokenizer ([`PreTrainedTokenizer`]): An instance of [`PreTrainedTokenizer`]. The tokenizer is a required input. rZ AutoTokenizercs t|||j|_d|_dS)NF)super__init__feature_extractorcurrent_processor_in_target_context_manager)selfr tokenizer __class__o/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/models/wav2vec2/processing_wav2vec2.pyr +szWav2Vec2Processor.__init__c sjztj|f|WStk rdtd|jdttj|f|}tj|f|}|||dYSXdS)NzLoading a tokenizer inside a from a config that does not include a `tokenizer_class` attribute is deprecated and will be removed in v5. Please add `'tokenizer_class': 'Wav2Vec2CTCTokenizer'` attribute to either your `config.json` or `tokenizer_config.json` file to suppress this warning: )r r) r from_pretrainedOSErrorwarningswarn__name__ FutureWarningrr)clsZpretrained_model_name_or_pathkwargsr rrrrr0s  z!Wav2Vec2Processor.from_pretrainedcOs|jr|j||Sd|kr0td|d}n |dd}|dd}|dd}t|dkrt|d}|dd}|dkr|dkrtd |dk r|j|f|d|i|}|dk r|j|f|}|dkr|S|dkr|S|d |d <|SdS) a When used in normal mode, this method forwards all its arguments to Wav2Vec2FeatureExtractor's [`~Wav2Vec2FeatureExtractor.__call__`] and returns its output. If used in the context [`~Wav2Vec2Processor.as_target_processor`] this method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.__call__`]. Please refer to the docstring of the above two methods for more information. Z raw_speechzLUsing `raw_speech` as a keyword argument is deprecated. Use `audio` instead.audioN sampling_ratetextrrzAYou need to specify either an `audio` or `text` input to process. input_idslabels) r r rrpoplen ValueErrorr r)rargsrrrrinputs encodingsrrr__call__Cs.         zWav2Vec2Processor.__call__cOs|jr|jj||S|dd}|dd}t|dkrL|d}|dd}|dk rh|jj|f||}|dk r|jj|f|}|dkr|S|dkr|S|d|d<|SdS)a When used in normal mode, this method forwards all its arguments to Wav2Vec2FeatureExtractor's [`~Wav2Vec2FeatureExtractor.pad`] and returns its output. If used in the context [`~Wav2Vec2Processor.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_featuresNr rrr)r r padr!r"r r)rr$rr(r rrrr)is"     zWav2Vec2Processor.padcOs|jj||S)z This method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r batch_decoderr$rrrrr*szWav2Vec2Processor.batch_decodecOs|jj||S)z This method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoder+rrrr,szWav2Vec2Processor.decodeccs0tdd|_|j|_dV|j|_d|_dS)z Temporarily sets the tokenizer for processing the input. Useful for encoding the labels when fine-tuning Wav2Vec2. 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)rrr rr r )rrrras_target_processorsz%Wav2Vec2Processor.as_target_processor)r __module__ __qualname____doc__Zfeature_extractor_classZtokenizer_classr classmethodrr'r)r*r,rr- __classcell__rrrrrs  &r) r0r contextlibrZprocessing_utilsrZfeature_extraction_wav2vec2rZtokenization_wav2vec2rrrrrrs