ale-dp's picture
Upload Dialogue Examples
723b51a verified
raw
history blame
2.5 kB
import streamlit as st
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
import torch
from examples import dialogue_examples
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.set_page_config(
page_title="Dialogue Summarizer App",
page_icon="ale.png", # You can set your own emoji or use an image URL
)
#logo_path = "ale.png"
#logo_html = f'<div style="text-align:center;"><img src="{logo_path}" width="200"></div>'
#st.markdown(logo_html, unsafe_allow_html=True)
# Display the app name below the logo
st.title("Dialogue Summarizer App")
st.info("\n🖥️ Note: This application is running on CPU. Please be patient ⏳.")
st.markdown("This app summarizes dialogues. Enter a short dialogue in the text area. For best results, keep the dialogues at least a few sentences. You can also use the examples provided at the bottom of the page.")
# Create two columns layout using st.columns
col1, col2 = st.columns(2)
# User input on the left side with increased height
user_input = col1.text_area("Enter a Dialogue:", height=300)
# Summary textbox on the right side with initial value (read-only)
initial_summary = "Generated Summary will appear here."
generated_summary = col2.text_area("Summary:", value=initial_summary, height=300, key="summary")
# Add "Summarize" and "Clear" buttons
summarize_button = col1.button("Summarize")
# If "Summarize" button is clicked and there is user input, generate and display summary in the summary textbox
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)
# Update the summary textbox with the generated summary
generated_summary.text(summary)
st.markdown("**Dialogue examples:**")
for idx, example in enumerate(dialogue_examples, 1):
st.write(f"Example {idx}:\n{example}")