app.py

import gradio as gr
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image
import requests

# Load the TrOCR model and processor
processor = TrOCRProcessor.from_pretrained('microsoft/trocr-large-printed')
model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-large-printed')

def extract_text_from_image(image_url):
    image = Image.open(requests.get(image_url, stream=True).raw).convert("RGB")
    pixel_values = processor(images=image, return_tensors="pt").pixel_values
    generated_ids = model.generate(pixel_values)
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return generated_text

# Create the Gradio interface
gr.Interface(
    fn=extract_text_from_image,
    inputs=gr.Textbox(label="Enter image URL:"),
    outputs=gr.Textbox(label="Extracted Text"),
    title="Text Extraction from Images",
    description="Extract text from an image using optical character recognition (OCR).",
).launch()