Spaces:
Runtime error
Runtime error
| import re | |
| from PIL import Image | |
| from transformers import DonutProcessor, VisionEncoderDecoderModel | |
| def get_result(image_path, question): | |
| processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa") | |
| model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa") | |
| # load document image from the DocVQA dataset | |
| image = Image.open(image_path).convert('RGB') | |
| # prepare decoder inputs | |
| task_prompt = "<s_docvqa><s_question>{user_input}</s_question><s_answer>" | |
| 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, | |
| decoder_input_ids=decoder_input_ids, | |
| max_length=model.decoder.config.max_position_embeddings, | |
| pad_token_id=processor.tokenizer.pad_token_id, | |
| eos_token_id=processor.tokenizer.eos_token_id, | |
| use_cache=True, | |
| 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)['answer'] | |