app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import speech_recognition as sr
import moviepy.editor as mp

def summarize_youtube_video(link):
    try:
        # Download and convert the YouTube video to audio
        video = mp.VideoFileClip(link)
        video.audio.write_audiofile("audio.wav")
        
        # Convert speech to text using Google Web Speech API
        recognizer = sr.Recognizer()
        with sr.AudioFile("audio.wav") as source:
            audio = recognizer.record(source)
        transcript = recognizer.recognize_google(audio)

        checkpoint = "facebook/bart-large-cnn"
        tokenizer = AutoTokenizer.from_pretrained(checkpoint)
        model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)

        inputs = tokenizer(transcript, 
                           max_length=1024, 
                           truncation=True,
                           return_tensors="pt")

        summary_ids = model.generate(inputs["input_ids"])
        summary = tokenizer.batch_decode(summary_ids, 
                                         skip_special_tokens=True, 
                                         clean_up_tokenization_spaces=False)

        return summary[0]
    except Exception as e:
        return "SummarizationError: Could not generate a summary"

# Define the input and output components for Gradio
inputs = gr.inputs.Textbox(label="YouTube Video Link")
outputs = gr.outputs.Textbox()

# Create the Gradio interface
gr.Interface(fn=summarize_youtube_video, inputs=inputs, outputs=outputs, title="YouTube Video Summarizer").launch(debug=True)