app.py

import streamlit as st
from pytube import YouTube
from moviepy.editor import *
import speech_recognition as sr
from transformers import pipeline
from pydub import AudioSegment
import os

def download_and_extract_audio(youtube_link):
    yt = YouTube(youtube_link)
    video = yt.streams.filter(only_audio=True).first()
    out_file = video.download(output_path=".")
    base, ext = os.path.splitext(out_file)
    new_file = base + '.mp3'
    os.rename(out_file, new_file)

    # Convert MP3 to WAV for compatibility with speech_recognition
    audio = AudioSegment.from_mp3(new_file)
    wav_file = base + '.wav'
    audio.export(wav_file, format="wav")
    return wav_file

def transcribe_audio(audio_path):
    recognizer = sr.Recognizer()
    with sr.AudioFile(audio_path) as source:
        audio_data = recognizer.record(source)
        text = recognizer.recognize_google(audio_data)
    return text

def summarize_text(text):
    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
    return summary[0]['summary_text']

def main():
    st.title("YouTube Video Summary")
    youtube_link = st.text_input("Enter YouTube Video Link:")
    if st.button("Summarize"):
        with st.spinner('Downloading and extracting audio...'):
            audio_path = download_and_extract_audio(youtube_link)
        with st.spinner('Transcribing audio to text...'):
            transcription = transcribe_audio(audio_path)
        with st.spinner('Summarizing transcription...'):
            summary = summarize_text(transcription)
        
        st.subheader("Transcription:")
        st.write(transcription)
        st.subheader("Summary:")
        st.write(summary)

if __name__ == '__main__':
    main()