invoice.py

import re

from PIL import Image
from transformers import DonutProcessor, VisionEncoderDecoderModel
from datasets import load_dataset
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)
# # load document image
# dataset = load_dataset("hf-internal-testing/example-documents", split="test")
# image = dataset[2]["image"]

with Image.open("invoice.jpg") as image:
    # prepare decoder inputs
    task_prompt = "<s_docvqa><s_question>What's the final total amount?</sep>What's the fax number of Company Name?</s_question><s_answer>"
    decoder_input_ids = processor.tokenizer(task_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,
        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))