src/streamlit_app.py

import streamlit as st
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

# Model name
MODEL_NAME = "AbdullahAlnemr1/flan-t5-summarizer"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)

st.title("Text Summarizer (Encoder-Decoder)")

input_text = st.text_area("Enter text summarize:", height=200)

# Fixed summary length
max_new_tokens = 100  # You can adjust this number

if st.button("Generate Summary"):
    if input_text.strip() == "":
        st.warning("Enter Text:")
    else:
        # Tokenize input
        inputs = tokenizer(input_text, return_tensors="pt", truncation=True)
        
        # Generate summary
        outputs = model.generate(
            inputs["input_ids"],
            max_new_tokens=max_new_tokens,
            num_beams=4,
            early_stopping=True
        )
        
        summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
        
        st.subheader("Summary:")
        st.write(summary)