app.py

import streamlit as st
from pytube import YouTube
from moviepy.editor import AudioFileClip
import speech_recognition as sr
from transformers import pipeline
import os

def download_and_extract_audio(youtube_link):
    try:
        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 using moviepy
        audio_clip = AudioFileClip(new_file)
        wav_file = base + '.wav'
        audio_clip.write_audiofile(wav_file, codec='pcm_s16le')  # codec for WAV format
        audio_clip.close()
        return wav_file
    except Exception as e:
        st.error(f"Error downloading and extracting audio: {e}")
        return None

def transcribe_audio(audio_path):
    try:
        recognizer = sr.Recognizer()
        with sr.AudioFile(audio_path) as source:
            audio_data = recognizer.record(source)
            text = recognizer.recognize_google(audio_data)
        return text
    except Exception as e:
        st.error(f"Error transcribing audio: {e}")
        return None

def summarize_text(text):
    try:
        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']
    except Exception as e:
        st.error(f"Error summarizing text: {e}")
        return None

def main():
    st.title("YouTube Video Summary")
    youtube_link = st.text_input("Enter YouTube Video Link:")
    if st.button("Summarize"):
        if youtube_link:
            with st.spinner('Downloading and extracting audio...'):
                audio_path = download_and_extract_audio(youtube_link)
                if audio_path is None:
                    return

            with st.spinner('Transcribing audio to text...'):
                transcription = transcribe_audio(audio_path)
                if transcription is None:
                    return

            with st.spinner('Summarizing transcription...'):
                summary = summarize_text(transcription)
                if summary is None:
                    return
            
            st.subheader("Transcription:")
            st.write(transcription)
            st.subheader("Summary:")
            st.write(summary)
        else:
            st.error("Please enter a valid YouTube video link.")

if __name__ == '__main__':
    main()