import streamlit as st
from transformers import T5Tokenizer, T5ForConditionalGeneration
import torch
# Load model and tokenizer from Hugging Face Hub
model_name = "t5-small" # or your model name
tokenizer = T5Tokenizer.from_pretrained(model_name)
model = T5ForConditionalGeneration.from_pretrained(model_name)
# Function to generate summary
def generate_summary(text):
inputs = ["summarize: " + text]
inputs = tokenizer(inputs, max_length=1024, truncation=True, return_tensors="pt")
outputs = model.generate(inputs.input_ids.to(model.device), max_length=150, length_penalty=2.0, num_beams=4, early_stopping=True)
return tokenizer.decode(outputs[0], skip_special_tokens=True)
# Custom CSS styling
st.markdown("""""", unsafe_allow_html=True)
# Application UI
st.title(" Text Summarizer App")
text = st.text_area("Enter the text you want to summarize...", height=200)
col1, col2 = st.columns(2)
with col1:
if st.button("Generate Summary"):
if text:
with st.spinner("Generating summary..."):
summary = generate_summary(text)
st.markdown('', unsafe_allow_html=True)
else:
st.warning("⚠️ Please enter text to summarize.")
with col2:
if st.button("Refresh"):
st.rerun() # change here
# Footer
st.markdown("""""", unsafe_allow_html=True)