Spaces:
Sleeping
Sleeping
import streamlit as st | |
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer | |
import torch | |
import sys | |
st.title("Dialog Summarizer App") | |
# User input | |
user_input = st.text_area("Enter the dialog:") | |
# Add "Summarize" and "Clear" buttons | |
summarize_button = st.button("Summarize") | |
clear_button = st.button("Clear") | |
# If "Clear" button is clicked, clear the user input | |
if clear_button: | |
user_input = "" | |
# "Summarize" button and user input, generate and display summary | |
if summarize_button and user_input: | |
# 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("Generated Summary:") | |
st.write(summary) | |
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 | |