import streamlit as st from transformers import AutoTokenizer, AutoModelForSeq2SeqLM # Load the tokenizer and model tokenizer = AutoTokenizer.from_pretrained("suriya7/bart-finetuned-text-summarization") model = AutoModelForSeq2SeqLM.from_pretrained("suriya7/bart-finetuned-text-summarization") def summarize_text(text): try: # Tokenize input with truncation to fit model requirements inputs = tokenizer([text], max_length=1024, return_tensors='pt', truncation=True) # Generate summary summary_ids = model.generate(inputs['input_ids'], max_length=150, num_beams=4, early_stopping=True) summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True) return summary except Exception as e: st.error(f"An error occurred: {e}") return "" # Initialize session state for input history if it doesn't exist if 'input_history' not in st.session_state: st.session_state['input_history'] = [] # Streamlit interface st.title("Text Summarizer") # User text inputs bulk_text = st.text_area("Enter the bulk text (e.g., client calls, meeting transcripts)", height=300) if st.button("Summarize Text"): if bulk_text: with st.spinner("Generating summary..."): summary = summarize_text(bulk_text) if summary: # Save the input and summary to the session state history st.session_state['input_history'].append({"text": bulk_text, "summary": summary}) st.subheader("Summary:") st.write(summary) else: st.warning("No summary was generated. Please check the input and try again.") else: st.warning("Please enter the bulk text.") # Display the history of inputs and summaries if st.session_state['input_history']: st.subheader("History") for i, entry in enumerate(st.session_state['input_history']): st.write(f"**Input {i+1} (Text):** {entry['text']}") st.write(f"**Summary {i+1}:** {entry['summary']}") st.write("---") # Instructions for using the app st.write("Enter your bulk text and click 'Summarize Text' to get a summary of the text.")