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

device = "cuda" if torch.cuda.is_available() else "cpu"

# Load the model
processor = TrOCRProcessor.from_pretrained("microsoft/trocr-large-handwritten")
model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-large-handwritten").to(device)

def ocr_infer(image):
    pixel_values = processor(images=image, return_tensors="pt").pixel_values.to(device)
    generated_ids = model.generate(pixel_values)
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return generated_text

# Gradio UI
iface = gr.Interface(
    fn=ocr_infer,
    inputs=gr.Image(type="pil"),
    outputs="text",
    title="Image to Text (OCR) ver7",
    description="Upload a handwritten or printed image to extract text using TrOCR."
)


iface.launch(share=True)