app.py

import streamlit as st
from PIL import Image
from transformers import TrOCRProcessor, VisionEncoderDecoderModel



# Create a file uploader widget
file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])

# Display the uploaded image
if file is not None:
    
    # Read the image data
    image = Image.open(file)
    image=image.convert("RGB")

    #resized_image = image.resize((384, 384))

    processor = TrOCRProcessor.from_pretrained('microsoft/trocr-base-handwritten')
    model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-handwritten')
    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]
    
    # Display the image
    st.image(image, caption='Uploaded Image', use_column_width=True)
    
    # Print the shape of the image
    st.write(f"Text: {generated_text} ")