import streamlit as st from transformers import AutoModelForSeq2SeqLM, AutoTokenizer import torch def generate_summary(model, tokenizer, dialogue): # Tokenize input dialogue inputs = tokenizer(dialogue, return_tensors="pt", max_length=1024, truncation=True) # Generate summary with torch.no_grad(): summary_ids = model.generate(inputs["input_ids"], max_length=150, length_penalty=0.8, num_beams=4) # Decode and return the summary summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=True) return summary st.title("Dialog Summarizer App") # User input user_input = st.text_area("Enter the dialog:") if not user_input: st.info("Please enter a dialog.") return # Load pre-trained Pegasus model and tokenizer model_name = "ale-dp/pegasus-finetuned-dialog-summarizer" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForSeq2SeqLM.from_pretrained(model_name) # Generate summary summary = generate_summary(model, tokenizer, user_input) # Display the generated summary st.subheader("Summary:") st.write(summary)