app.py

"""
Donut
Copyright (c) 2022-present NAVER Corp.
MIT License
https://github.com/clovaai/donut
"""
import gradio as gr
import os
import logging
import torch
from PIL import Image

from donut import DonutModel

def demo_process(input_img):
    global pretrained_model, task_prompt, task_name
    # input_img = Image.fromarray(input_img)
    output = pretrained_model.inference(image=input_img, prompt=task_prompt)["predictions"][0]
    return output

task_prompt = f"<s_cord-v2>"


pretrained_model = DonutModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
pretrained_model.encoder.to(torch.bfloat16)
pretrained_model.eval()

demo = gr.Interface(
    fn=demo_process,
    inputs= gr.inputs.Image(type="pil"),
    outputs="json",
    title=f"Demo for `cord-v2` task",
    description=f"Description for `cord-v2` task",
    cache_examples=False,
)
demo.launch()