app.py

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

# Streamlit app
st.title("Handwritten Text Recognition")

# Upload an image
uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])

if uploaded_file is not None:
    image = Image.open(uploaded_file).convert("RGB")
    st.image(image, caption='Uploaded Image', use_column_width=True)
    
    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]
    
    st.write("Recognized Text:")
    st.write(generated_text)