app.py

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

# Load processor + model
processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")

def ocr_image(image):
    # Convert to PIL Image if uploaded
    if not isinstance(image, Image.Image):
        image = Image.fromarray(image)

    pixel_values = processor(images=image, return_tensors="pt").pixel_values
    generated_ids = model.generate(pixel_values)
    text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return text

demo = gr.Interface(
    fn=ocr_image,
    inputs=gr.Image(type="pil"),     # Image upload box
    outputs=gr.Textbox(label="Extracted Text")  # Show extracted text
)

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