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

# Load the processor and model
processor = TrOCRProcessor.from_pretrained('microsoft/trocr-large-stage1')
model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-large-stage1')

def generate_text(input_image):
    # Convert Gradio input image to PIL Image
    image = Image.fromarray(input_image)
    # Process the image and generate text
    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

# Define the Gradio interface
iface = gr.Interface(
    fn=generate_text,
    inputs=gr.Image(),  # Gradio Image input
    outputs=gr.Textbox(),  # Gradio Textbox output
)

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