gdZddlZddlmZddlmZmZmZddlm Z m Z m Z ddl m Z mZmZdd lmZdd lmZGd d e d ZGdde ZdS)z% Speech processor class for Wav2Vec2 N)contextmanager)ListOptionalUnion)ProcessingKwargsProcessorMixinUnpack) AudioInputPreTokenizedInput TextInput)Wav2Vec2FeatureExtractor)Wav2Vec2CTCTokenizerceZdZiZdS)Wav2Vec2ProcessorKwargsN)__name__ __module__ __qualname__ _defaultsl/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/wav2vec2/processing_wav2vec2.pyrrsIIIrrF)totalc eZdZdZdZdZfdZefdZ dde de e e e e eefd eefd Zd Zd Zd ZedZxZS)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. r AutoTokenizercrt|||j|_d|_dS)NF)super__init__feature_extractorcurrent_processor_in_target_context_manager)selfr! tokenizer __class__s rr zWav2Vec2Processor.__init__3s7 *I666!%!7*/'''rc  tj|fi|S#ttf$rWt jd|jdttj|fi|}tj|fi|}|||cYSwxYw)NzLoading a tokenizer inside a from a config that does not include a `tokenizer_class` attribute is deprecated and will be removed in v5. Please add `'tokenizer_class': 'Wav2Vec2CTCTokenizer'` attribute to either your `config.json` or `tokenizer_config.json` file to suppress this warning: )r!r%) rfrom_pretrainedOSError ValueErrorwarningswarnr FutureWarningrr)clspretrained_model_name_or_pathkwargsr!r%r&s rr(z!Wav2Vec2Processor.from_pretrained8s Q*577*+HSSFSS S$ Q Q Q M2cl222     !9 HIf q qjp q q ,<=Zee^deeI3):iPPP P P P QsA%BBNaudiotextr0c d|vr)tjd|d}||td|jt fd|jji|}|jr$|j |fi|d|d|dS||j |fi|d}||j|fi|d}||S||S|d |d <|S) a When used in normal mode, this method forwards all its arguments to Wav2Vec2FeatureExtractor's [`~Wav2Vec2FeatureExtractor.__call__`] and returns its output. If used in the context [`~Wav2Vec2Processor.as_target_processor`] this method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.__call__`]. Please refer to the docstring of the above two methods for more information. raw_speechzLUsing `raw_speech` as a keyword argument is deprecated. Use `audio` instead.NzAYou need to specify either an `audio` or `text` input to process.tokenizer_init_kwargs audio_kwargs text_kwargs common_kwargs input_idslabels) r+r,popr* _merge_kwargsrr% init_kwargsr#r"r!) r$r1r2imagesvideosr0 output_kwargsinputs encodingss r__call__zWav2Vec2Processor.__call__KsG 6 ! ! Mh i i iJJ|,,E =T\`aa a** #  "&."<    * )4)/ . 0    +T+ESS]>5RSSF  &tLL}]/KLLI <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 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:rrr9)r#r"padr;lenr!r%)r$argsr0rEr:s rrFzWav2Vec2Processor.pad|s  * ?-4)-t>v>> >$4d;;Hd++ t99q==!!WN8D  %7T37XXXXQWXXN  'T^'99&99F >! !  #M'-k':N8 $! !rc&|jj|i|S)z This method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r% batch_decoder$rHr0s rrJzWav2Vec2Processor.batch_decodes +t~*D;F;;;rc&|jj|i|S)z This method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r%decoderKs rrMzWav2Vec2Processor.decodes %t~$d5f555rc#Ktjdd|_|j|_dV|j|_d|_dS)z Temporarily sets the tokenizer for processing the input. Useful for encoding the labels when fine-tuning Wav2Vec2. z`as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your audio inputs, or in a separate call.TNF)r+r,r#r%r"r!)r$s ras_target_processorz%Wav2Vec2Processor.as_target_processorsW   8   +/'!% !%!7*/'''r)NNNN)rrr__doc__feature_extractor_classtokenizer_classr classmethodr(r rrstrrr r r rrCrFrJrMrrO __classcell__)r&s@rrr!s#  9%O00000 QQQQ[Q(!NR ///uS$s)Y8IIJK/ 01 ////b"""<<<<66600^00000rr)rPr+ contextlibrtypingrrrprocessing_utilsrr r tokenization_utils_baser r r feature_extraction_wav2vec2rtokenization_wav2vec2rrrrrrr\s%%%%%%((((((((((HHHHHHHHHHOOOOOOOOOOAAAAAA777777.eV0V0V0V0V0V0V0V0V0V0r