| """ | |
| Donut | |
| Copyright (c) 2022-present NAVER Corp. | |
| MIT License | |
| https://github.com/clovaai/donut | |
| """ | |
| import gradio as gr | |
| 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>" | |
| image = Image.open("./sample_image_cord_test_receipt_00004.jpg") | |
| image.save("cord_sample_receipt.jpg") | |
| 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"Donut 🍩 demonstration for `cord-v2` task", | |
| examples=[["cord_sample_receipt.jpg"]], | |
| ) | |
| demo.launch(debug=True) | |