app.py

import streamlit as st
import io
from PIL import Image
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from easyocr import Reader


ocr_reader = Reader(['en'])
text_generator = AutoModelForCausalLM.from_pretrained("gpt2")
text_tokenizer = AutoTokenizer.from_pretrained("gpt2")
def extract_text(image):
    return ocr_reader.readtext(image)
def explain_text(text):
    input_ids = text_tokenizer.encode(text, return_tensors="pt")
    explanation_ids = text_generator.generate(input_ids, max_length=100, num_return_sequences=1)
    explanation = text_tokenizer.decode(explanation_ids[0], skip_special_tokens=True)
    return explanation

st.title("Text Classification Model")
uploaded_file = st.file_uploader("Upload an image:")

if uploaded_file is not None:
    image = Image.open(uploaded_file)
    ocr_results = extract_text(image)
    extracted_text = " ".join([res[1] for res in ocr_results])
    explanation = explain_text(extracted_text)
    st.markdown("**Extracted text:**")
    st.markdown(extracted_text)

    st.markdown("**Explanation:**")
    st.markdown(explanation)

else:
    st.markdown("Please upload an image to extract text and get an explanation.")