import gradio as gr
import torch
from transformers import VisionEncoderDecoderModel, TrOCRProcessor

# Load the model and processor
processor = TrOCRProcessor.from_pretrained('microsoft/trocr-base-handwritten')
model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-handwritten')

# Define a function to perform OCR
def perform_ocr(image):
    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 a Gradio interface
iface = gr.Interface(
    fn=perform_ocr,
    inputs="image",
    outputs="text",
    title="Image OCR",
    description="Upload an image to extract text"
)

# Launch the interface
iface.launch()