o h @s$dZddlmZGdddeZdS)z Processor class for TVLT. )ProcessorMixincsReZdZdZddgZdZdZfddZ     dd d Ze d d Z Z S) TvltProcessora` Constructs a TVLT processor which wraps a TVLT image processor and TVLT feature extractor into a single processor. [`TvltProcessor`] offers all the functionalities of [`TvltImageProcessor`] and [`TvltFeatureExtractor`]. See the docstring of [`~TvltProcessor.__call__`] for more information. Args: image_processor (`TvltImageProcessor`): An instance of [`TvltImageProcessor`]. The image processor is a required input. feature_extractor (`TvltFeatureExtractor`): An instance of [`TvltFeatureExtractor`]. The feature extractor is a required input. image_processorfeature_extractorTvltImageProcessorTvltFeatureExtractorcs tj||d||_||_dS)N)rr)super__init__rr)selfrr __class__^/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/tvlt/processing_tvlt.pyr (s zTvltProcessor.__init__NFc Os|dur |dur tdd} |dur |j|g|Rd|i|} |dur2|j|g|Rddi|} |durE|j|g|R||d|} i} |durP| | |durY| | | durb| | | S)a Forwards the `images` argument to TvltImageProcessor's [`~TvltImageProcessor.preprocess`] and the `audio` argument to TvltFeatureExtractor's [`~TvltFeatureExtractor.__call__`]. Please refer to the docstring of the above two methods for more information. NzCYou need to specify either an `images` or `audio` input to process. mask_pixelis_mixedT) sampling_rate mask_audio) ValueErrorrrupdate) r imagesaudio images_mixedrrrargskwargsimages_mixed_dict images_dict audio_dict output_dictr r r__call__.s2   zTvltProcessor.__call__cCs"|jj}|jj}tt||S)N)rmodel_input_namesrlistdictfromkeys)r image_processor_input_namesfeature_extractor_input_namesr r rrUszTvltProcessor.model_input_names)NNNNFF) __name__ __module__ __qualname____doc__ attributesimage_processor_classfeature_extractor_classr rpropertyr __classcell__r r r rrs   'rN)r(processing_utilsrrr r r rs