Spaces:
Running
Running
File size: 1,337 Bytes
5b9baff ab9088f 5b9baff ab9088f 5b9baff ab9088f 5b9baff ab9088f 5b9baff ab9088f 5b9baff |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
import json, base64
from io import BytesIO
from PIL import Image
import gradio as gr
from inference import OcrReorderPipeline
from transformers import (
AutoProcessor,
LayoutLMv3Model,
AutoTokenizer
)
import torch
# 1) Load from your model repo, pointing at the `preprocessor/` folder
repo = "Uddipan107/ocr-layoutlmv3-base-t5-small"
model = LayoutLMv3Model.from_pretrained(repo)
tokenizer = AutoTokenizer.from_pretrained(repo, subfolder="preprocessor")
processor = AutoProcessor.from_pretrained(repo, subfolder="preprocessor", apply_ocr=False)
# 2) Instantiate your pipeline
pipe = OcrReorderPipeline(model, tokenizer, processor, device=0)
def infer(image, words_json, boxes_json):
words = json.loads(words_json)
boxes = json.loads(boxes_json)
# Encode PIL image → PNG → base64
buf = BytesIO()
image.save(buf, format="PNG")
b64 = base64.b64encode(buf.getvalue()).decode()
# Run your custom pipeline and return the first (only) output string
return pipe(b64, words, boxes)[0]
# 3) Gradio UI
demo = gr.Interface(
fn=infer,
inputs=[
gr.Image(type="pil", label="Image"),
gr.Textbox(label="Words (JSON list)"),
gr.Textbox(label="Boxes (JSON list)")
],
outputs="text",
title="OCR Reorder Pipeline"
)
if __name__ == "__main__":
demo.launch()
|