app.py

import re
import gradio as gr

import torch
from transformers import DonutProcessor, VisionEncoderDecoderModel

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 process_document(image, question):
    # prepare encoder inputs
    pixel_values = processor(image, return_tensors="pt").pixel_values
    
    # 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
          
    # generate answer
    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,
    )
    
    # postprocess
    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
    
    return processor.token2json(sequence)

description ="""
<p>
<center>
Demo de OCR, el objetivo es preguntar al documento y que este extraiga la información .
<img src="https://raw.githubusercontent.com/All-Aideas/sea_apirest/main/logo.png" alt="logo" width="250"/>
</center>
</p>
"""

article = "<p style='text-align: center'><a href='http://allaideas.com/index.html' target='_blank'>Ocrask: Link para mas info</a> </p>"

demo = gr.Interface(
    fn=process_document,
    inputs=["image", "text"],
    outputs="json",
    title="Demo: OCRASK  📸",
    description=description,
    article=article,
    enable_queue=True,
    examples=[["ab.jpg", "mount?"],["example_1.png", "When is the coffee break?"], ["example_2.jpeg", "What's the population of Stoddard?"]],
    cache_examples=False)

demo.launch()