import re import gradio as gr from transformers import DonutProcessor, VisionEncoderDecoderModel import torch processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa") model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa") device = "cuda" if torch.cuda.is_available() else "cpu" model.to(device) def doc_process(image,question): # prepare decoder inputs task_prompt = "{user_input}" prompt = task_prompt.replace("{user_input}", question) decoder_input_ids = processor.tokenizer(prompt, add_special_tokens=False, return_tensors="pt").input_ids pixel_values = processor(image, return_tensors="pt").pixel_values outputs = model.generate( pixel_values.to(device), decoder_input_ids=decoder_input_ids.to(device), max_length=model.decoder.config.max_position_embeddings, early_stopping=True, pad_token_id=processor.tokenizer.pad_token_id, eos_token_id=processor.tokenizer.eos_token_id, use_cache=True, num_beams=1, bad_words_ids=[[processor.tokenizer.unk_token_id]], return_dict_in_generate=True, ) sequence = processor.batch_decode(outputs.sequences)[0] sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "") sequence = re.sub(r"<.*?>", "", sequence, count=1).strip() # remove first task start token #print(processor.token2json(sequence)) return processor.token2json(sequence) description = "Gradio Demo for Donut 🍩, inspired by Nielsr demo" article = "

Donut: OCR-free Document Understanding Transformer | Github Repo

" demo = gr.Interface( fn= doc_process, inputs=["image", "text"], outputs="json", title="Donut 🍩 for DocVQA", description=description, article=article, enable_queue=True, examples=[["example_1.png", "What is date of birth?"], ["example_1.png", "What is Patient initials?"]], cache_examples=False) demo.launch()