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

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

def extract_text(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

# Gradio interface
iface = gr.Interface(
    fn=extract_text,
    inputs=gr.inputs.Image(type="pil"),
    outputs="text",
    title="OCR Text Extraction",
    description="Extract printed text from images."
)

iface.launch()