app.py

import re
from transformers import DonutProcessor, VisionEncoderDecoderModel
from datasets import load_dataset
from PIL import Image
import torch
import gradio as gr

#image = gr.Image(shape=(224, 224))
processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

def classify_image(inp):
    task_prompt = "<s_cord-v2>"
    decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids
    pixel_values = processor(inp, 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
    return processor.token2json(sequence)

#title = "Gradio Image Reading"
#gr.Interface(fn=classify_image,"image","text").launch()
gr.Interface(classify_image, "image","text").launch()