app.py

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




def load_image(image_file):
	img = PIL.Image.open(image_file)
	return img



uploaded_file = st.file_uploader("Upload Files",type=['png','jpeg','jpg'])
if uploaded_file is not None:
    file_details = {"FileName":uploaded_file.name,"FileType":uploaded_file.type,"FileSize":uploaded_file.size}
    st.write(file_details)
    image = load_image(uploaded_file)
    st.image(image,width=250)
    processor = TrOCRProcessor.from_pretrained("microsoft/trocr-large-handwritten") 
    model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-large-handwritten")
    image = image.convert("RGB")
    pixel_values = processor(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(generated_text)