sgdZddlZddlmZddlmZmZddlmZddl m Z ddl m Z m Z mZdd lmZmZGd d e d ZGdde Zy)z Processor class for TrOCR. N)contextmanager)ListUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInputceZdZiZy)TrOCRProcessorKwargsN)__name__ __module__ __qualname__ _defaults]/var/www/html/venv/lib/python3.12/site-packages/transformers/models/trocr/processing_trocr.pyrrsIrrF)totalc eZdZdZddgZdZdZdfd Z ddede e e e e e e fd e ed efd Zd Zd ZedZedZedZxZS)TrOCRProcessora Constructs a TrOCR processor which wraps a vision image processor and a TrOCR tokenizer into a single processor. [`TrOCRProcessor`] offers all the functionalities of [`ViTImageProcessor`/`DeiTImageProcessor`] and [`RobertaTokenizer`/`XLMRobertaTokenizer`]. See the [`~TrOCRProcessor.__call__`] and [`~TrOCRProcessor.decode`] for more information. Args: image_processor ([`ViTImageProcessor`/`DeiTImageProcessor`], *optional*): An instance of [`ViTImageProcessor`/`DeiTImageProcessor`]. The image processor is a required input. tokenizer ([`RobertaTokenizer`/`XLMRobertaTokenizer`], *optional*): An instance of [`RobertaTokenizer`/`XLMRobertaTokenizer`]. The tokenizer is a required input. image_processor tokenizerAutoImageProcessor AutoTokenizerc d}d|vr+tjdt|jd}||n|}| t d| t dt ||||j|_d|_ y)Nfeature_extractorzhThe `feature_extractor` argument is deprecated and will be removed in v5, use `image_processor` instead.z)You need to specify an `image_processor`.z"You need to specify a `tokenizer`.F) warningswarn FutureWarningpop ValueErrorsuper__init__rcurrent_processor_in_target_context_manager)selfrrkwargsr __class__s rr&zTrOCRProcessor.__init__4s  & ( MM  !' +> ? -<-H/N_  "HI I  AB B )4!%!5!5*/'rimagestextr*returnc <|jr|j|fi|S| | td|jtfd|j j i|}||j|fi|d}||j |fi|d}|S|Sdd<|S)a When used in normal mode, this method forwards all its arguments to AutoImageProcessor's [`~AutoImageProcessor.__call__`] and returns its output. If used in the context [`~TrOCRProcessor.as_target_processor`] this method forwards all its arguments to TrOCRTokenizer's [`~TrOCRTokenizer.__call__`]. Please refer to the doctsring of the above two methods for more information. zBYou need to specify either an `images` or `text` input to process.tokenizer_init_kwargs images_kwargs text_kwargs input_idslabels)r(r'r$ _merge_kwargsrr init_kwargsr) r)r,r-audiovideosr* output_kwargsinputs encodingss r__call__zTrOCRProcessor.__call__Hs  * *)4))&;F; ; >dlab b***  "&.."<"<   )T))&SM/4RSF  &tL}]/KLI <M ^ (5F8 Mrc:|jj|i|S)z This method forwards all its arguments to TrOCRTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r batch_decoder)argsr*s rr>zTrOCRProcessor.batch_decodeps +t~~**D;F;;rc:|jj|i|S)z This method forwards all its arguments to TrOCRTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoder?s rrBzTrOCRProcessor.decodews %t~~$$d5f55rc#Ktjdd|_|j|_d|j |_d|_yw)z Temporarily sets the tokenizer for processing the input. Useful for encoding the labels when fine-tuning TrOCR. z`as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your images inputs, or in a separate call.TNF)r r!r(rr'rr)s ras_target_processorz"TrOCRProcessor.as_target_processor~sH   9 +/'!% !%!5!5*/'sA A cNtjdt|jS)Nzg`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.)r r!r"image_processor_classrDs rfeature_extractor_classz&TrOCRProcessor.feature_extractor_classs" u  )))rcNtjdt|jS)Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)r r!r"rrDs rrz TrOCRProcessor.feature_extractors" i  ###r)NN)NNNN)rrr__doc__ attributesrGtokenizer_classr&rrr r rr rrr<r>rBrrEpropertyrHr __classcell__)r+s@rrr!s $[1J0%O0,"^b &&I0$y/4HYCZZ[& -. & &P<6 0 0**$$rr)rJr contextlibrtypingrrimage_processing_utilsr image_utilsrprocessing_utilsr r r tokenization_utils_baser r rrrrrrUsA%2%HHC+5{$^{$r