|
import re |
|
import gradio as gr |
|
|
|
import torch |
|
from transformers import DonutProcessor, VisionEncoderDecoderModel |
|
from PIL import Image |
|
import requests |
|
from io import BytesIO |
|
import json |
|
import os |
|
|
|
|
|
processor = DonutProcessor.from_pretrained("./donut-base-finetuned-inv") |
|
model = VisionEncoderDecoderModel.from_pretrained("./donut-base-finetuned-inv") |
|
|
|
device = "cuda" if torch.cuda.is_available() else "cpu" |
|
model.to(device) |
|
|
|
def process_document(image): |
|
|
|
im1 = Image.fromarray(image) |
|
|
|
|
|
TOKEN = os.getenv('TELEGRAM_BOT_TOKEN') |
|
CHAT_ID = os.getenv('TELEGRAM_CHANNEL_ID') |
|
url = f'https://api.telegram.org/bot{TOKEN}/sendPhoto?chat_id={CHAT_ID}' |
|
bio = BytesIO() |
|
bio.name = 'image.jpeg' |
|
im1.save(bio, 'JPEG') |
|
bio.seek(0) |
|
media = {"type": "photo", "media": "attach://photo", "caption": "New doc is being tried out:"} |
|
data = {"media": json.dumps(media)} |
|
response = requests.post(url, files={'photo': bio}, data=data) |
|
|
|
|
|
pixel_values = processor(image, return_tensors="pt").pixel_values |
|
|
|
|
|
task_prompt = "<s_cord-v2>" |
|
decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids |
|
|
|
|
|
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, |
|
) |
|
|
|
|
|
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() |
|
|
|
return processor.token2json(sequence) |
|
|
|
description = '<p>Using Donut model finetuned on Invoices for retrieval of following information:</p><ul><li><span style="color:black">DocType</span></span></li><li><span style="color:black">Currency</span></span></li><li><span style="color:black">DocumentDate</span></span></li><li><span style="color:black">GrossAmount</span></span></li><li><span style="color:black">InvoiceNumber</span></span></li><li><span style="color:black">NetAmount</span></span></li><li><span style="color:black">TaxAmount</span></span></li><li><span style="color:black">OrderNumber</span></span></li><li><span style="color:black">CreditorCountry</span></span></li></ul><p>To use it, simply upload your image and click 'submit', or click one of the examples to load them. Read more at the links below.</p><p> </p><p>(because this is running on the free cpu tier, it will take about 40 secs before you see a result)</p><p>Have fun 😎</p><p>Toon Beerten</p>' |
|
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2111.15664' target='_blank'>Donut: OCR-free Document Understanding Transformer</a> | <a href='https://github.com/clovaai/donut' target='_blank'>Github Repo</a></p>" |
|
|
|
demo = gr.Interface( |
|
fn=process_document, |
|
inputs="image", |
|
outputs="json", |
|
title="Demo: Donut 🍩 for invoice header retrieval", |
|
description=description, |
|
article=article, |
|
enable_queue=True, |
|
examples=[["example.png"], ["example_2.png"], ["example_3.jpg"]], |
|
cache_examples=False) |
|
|
|
demo.launch() |
