app.py

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

processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-rvlcdip")
model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-rvlcdip")

def ClassificateDocs(pathimage):
  image = Image.open(pathimage)
  pixel_values = processor(image, return_tensors="pt").pixel_values
  task_prompt = "<s_rvlcdip>"
  decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids
  device = "cuda" if torch.cuda.is_available() else "cpu"
  model.to(device)
  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)
ClassificateDocs("/content/Factura3.jpeg")
demo = gr.Blocks()

gradio_app = gr.Interface(
    fn=ClassificateDocs,
    inputs=[
        gr.Image(type='filepath')
    ],
    outputs="text",
)

if __name__ == "__main__":
    gradio_app.launch()