application.py

import streamlit as st
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

# Set page title and header
st.set_page_config(page_title="Text Summarizer", page_icon=":memo:")
st.header("Text Summarizer using Arjun9/bart_samsum")

# Load model and tokenizer
model_name = "Arjun9/bart_samsum"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

# Create text input area
input_text = st.text_area("Enter the text you want to summarize:", "")

# Create a function to generate summary
def generate_summary(text):
    inputs = tokenizer.encode_plus(text, return_tensors="pt", max_length=512, truncation=True)
    outputs = model.generate(inputs["input_ids"], num_beams=4, max_length=128, early_stopping=True)
    summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return summary

# Display summary if input text is provided
if input_text:
    summary = generate_summary(input_text)
    st.write("**Summary:**", summary)