app.py

import streamlit as st
from transformers import pipeline
from heapq import nlargest

# Function to extract text from SRT-formatted text
def extract_text_from_srt_text(srt_text):
    lines = srt_text.strip().split("\n\n")  # Split by empty lines to separate subtitles
    texts = [subtitle.split("\n")[2] for subtitle in lines if subtitle.strip()]  # Extract text from the third line of each subtitle
    return " ".join(texts)

# Function to generate summary from text
def generate_summary(text, summary_length):
    summarizer = pipeline("summarization")
    summary = summarizer(text, max_length=summary_length, min_length=30, do_sample=False)
    summary_text = summary[0]["summary_text"]
    sentences = text.split(". ")
    top_sentences = nlargest(4, sentences, key=len)
    top_subjects = "\n".join(top_sentences)
    return summary_text, top_subjects

# Streamlit app
st.title("SRT Summarization")

# Text area for user to input SRT-formatted text
srt_text_input = st.text_area("Paste SRT-formatted text here:")

# Button to trigger summarization
if st.button("Summarize"):
    # Check if text area is not empty
    if srt_text_input.strip():
        # Show loading spinner while processing
        with st.spinner("Summarizing..."):
            # Extract text from SRT-formatted text
            text_to_summarize = extract_text_from_srt_text(srt_text_input)
            # Generate summary and top subjects
            summary, top_subjects = generate_summary(text_to_summarize, 150)  # You can adjust the summary length as needed
            # Display summary and top subjects
            st.subheader("Summary:")
            st.write(summary)
            st.subheader("Top 4 Subjects:")
            st.write(top_subjects, bullet=True)  # Display as bullet points
    else:
        st.warning("Please enter some SRT-formatted text.")