app.py

import whisper
from pytubefix import YouTube
from pytubefix.cli import on_progress
from transformers import pipeline
import gradio as gr
import os 

model = whisper.load_model("base")
summarizer = pipeline("summarization") 

def get_audio(url):
    yt = YouTube(url, on_progress_callback=on_progress)
    audio_stream = yt.streams.get_audio_only()
    out_file = audio_stream.download(mp3=True)  # This will directly download as mp3
    return out_file  # Returns the path to the mp3 file

def get_text(url):
    result = model.transcribe(get_audio(url))
    return result['text']

def get_summary(url):
    article = get_text(url)
    b = summarizer(article)
    b = b[0]['summary_text']
    return b

with gr.Blocks() as demo:
    gr.Markdown("<h1><center>Youtube video transcription with OpenAI's Whisper</center></h1>")
    gr.Markdown("<center>Enter the link of any youtube video to get the transcription of the video and a summary of the video in the form of text.</center>")
    
    with gr.Tab('Get the transcription of any Youtube video'):
        with gr.Row():
            input_text_1 = gr.Textbox(placeholder='Enter the Youtube video URL', label='URL')
            output_text_1 = gr.Textbox(placeholder='Transcription of the video', label='Transcription')
        result_button_1 = gr.Button('Get Transcription')
        
    with gr.Tab('Summary of Youtube video'):
        with gr.Row():
            input_text = gr.Textbox(placeholder='Enter the Youtube video URL', label='URL')
            output_text = gr.Textbox(placeholder='Summary text of the Youtube Video', label='Summary')
        result_button = gr.Button('Get Summary')

    result_button.click(get_summary, inputs = input_text, outputs = output_text)
    result_button_1.click(get_text, inputs = input_text_1, outputs = output_text_1)

demo.launch(debug=True)