app.py

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

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

st.title("✍ Handwritten Text Extractor (OCR)")
st.write("Upload a handwritten image and extract text using AI")

uploaded_file = st.file_uploader("Upload Handwritten Image", type=["jpg", "png", "jpeg"])

if uploaded_file:
    image = Image.open(uploaded_file).convert("RGB")
    st.image(image, caption="Uploaded Handwriting", use_column_width=True)

    # Run OCR
    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]

    st.subheader("Extracted Text:")
    st.success(text)