sgdZddlZddlmZddlmZmZmZddlm Z m Z m Z ddl m Z mZmZdd lmZdd lmZGd d e d ZGdde Zy)z% Speech processor class for Wav2Vec2 N)contextmanager)ListOptionalUnion)ProcessingKwargsProcessorMixinUnpack) AudioInputPreTokenizedInput TextInput)Wav2Vec2FeatureExtractor)Wav2Vec2CTCTokenizerceZdZiZy)Wav2Vec2ProcessorKwargsN)__name__ __module__ __qualname__ _defaultsc/var/www/html/venv/lib/python3.12/site-packages/transformers/models/wav2vec2/processing_wav2vec2.pyrrsIrrF)totalc eZdZdZdZdZfdZefdZ dde de e e e e eefdeefd Zd Zd Zd Zed ZxZS)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 AutoTokenizercVt||||j|_d|_y)NF)super__init__feature_extractorcurrent_processor_in_target_context_manager)selfr! tokenizer __class__s rr zWav2Vec2Processor.__init__3s) *I6!%!7!7*/'rc  t||fi|S#ttf$rat j d|j dttj|fi|}tj|fi|}|||cYSwxYw)NzLoading a tokenizer inside a from a config that does not include a `tokenizer_class` attribute is deprecated and will be removed in v5. Please add `'tokenizer_class': 'Wav2Vec2CTCTokenizer'` attribute to either your `config.json` or `tokenizer_config.json` file to suppress this warning: )r!r%) rfrom_pretrainedOSError ValueErrorwarningswarnr FutureWarningrr)clspretrained_model_name_or_pathkwargsr!r%r&s rr(z!Wav2Vec2Processor.from_pretrained8s Q7*+HSFS S$ Q MM-cll^<22   !9 H HIf qjp q ,<<=Ze^deI):iP P QsA-BBaudiotextr0c d|vr&tjd|jd}| | td|jt fd|j ji|}|jr |j|fi|d|d|dS||j|fi|d}||j |fi|d}|S|Sdd <|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.zAYou 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$r1r2imagesvideosr0 output_kwargsinputs encodingss r__call__zWav2Vec2Processor.__call__Ks( 6 ! MMh iJJ|,E =T\`a a*** # "&.."<"<   * *)4))/ . 0    +T++ES]>5RSF  &tL}]/KLI <M ] (5F8 Mrcp|jr|jj|i|S|jdd}|jdd}t |dkDr |d}|dd}| |j j|g|i|}||j j|fi|}||S||S|d|d<|S)a When used in normal mode, this method forwards all its arguments to Wav2Vec2FeatureExtractor's [`~Wav2Vec2FeatureExtractor.pad`] and returns its output. If used in the context [`~Wav2Vec2Processor.as_target_processor`] this method forwards all its arguments to PreTrainedTokenizer's [`~PreTrainedTokenizer.pad`]. Please refer to the docstring of the above two methods for more information. input_featuresNr:rrr9)r#r"padr;lenr!r%)r$argsr0rEr:s rrFzWav2Vec2Processor.pad|s  * *-4))--t>v> >$4d;Hd+ t9q=!!WN8D  %7T3377XXQWXN  'T^^''9&9F >! !  #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~~$$d5f55rc#Ktjdd|_|j|_d|j |_d|_yw)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$s ras_target_processorz%Wav2Vec2Processor.as_target_processorsH   8 +/'!% !%!7!7*/'sA A )NNNN)rrr__doc__feature_extractor_classtokenizer_classr classmethodr(r rrstrrr r r rrCrFrJrMrrO __classcell__)r&s@rrr!s 9%O0 QQ(!NR //uS$s)Y8IIJK/ 01 /b"<<600rr)rPr+ contextlibrtypingrrrprocessing_utilsrr r tokenization_utils_baser r r feature_extraction_wav2vec2rtokenization_wav2vec2rrrrrrr\sG%((HHOOA7.eV0V0r