app.py

import gradio as gr
from PIL import Image
from support import processor
import os

os.system("pip install -r requirements.txt")
os.system('chmod 777 /tmp')
os.system('apt-get update -y')
os.system('apt-get install tesseract-ocr -y')
os.system('pip install -q pytesseract')

def OCR_processor(input_image):
    ##input_image = Image.open(input_image)
    return processor(input_image)

examples =[['eg1.png'],['eg2.png'],['eg3.png']]
iface = gr.Interface(
    fn=OCR_processor,
    inputs=gr.inputs.Image(type="pil", label="Upload an Image"),
    outputs=gr.outputs.Image(type="pil", label="Processed Image"),
    title="Form understanding using Multimodal Transformers",
    examples=examples,
    description="Upload an image, and the app will process it using the LayoutLMV3 multimodal transformer. You can get all the OCR tags marked in the image as output.",
    theme="huggingface",  # You can use "default", "compact", or "huggingface" themes
    layout="vertical",
    live=True,
)

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