app.py

import gradio as gr
from transformers import BartForConditionalGeneration, BartTokenizer
from youtube_transcript_api import YouTubeTranscriptApi

# Load BART model and tokenizer
model_name = 'facebook/bart-large-cnn'
tokenizer = BartTokenizer.from_pretrained(model_name)
model = BartForConditionalGeneration.from_pretrained(model_name)

def get_transcript(url):
    try:
        video_id = url.split('=')[1]
        transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
        transcript_text = ""
        for item in transcript_list:
            transcript_text += item['text'] + "\n"
        return transcript_text
    except Exception as e:
        return "Error fetching transcript: " + str(e)

def summarize_transcript(transcript):
    input_ids = tokenizer.encode("summarize: " + transcript, return_tensors="pt", max_length=1024, truncation=True)
    summary_ids = model.generate(input_ids, num_beams=4, min_length=30, max_length=200, early_stopping=True)
    summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
    return summary

def summarize_video_url(video_url):
    transcript = get_transcript(video_url)
    if not transcript:
        return "Error fetching transcript."
    else:
        summary = summarize_transcript(transcript)
        return summary

input = gr.inputs.Textbox(label="Enter YouTube Video URL")
output = gr.outputs.Textbox(label="Summary")

title = "YouTube Video Transcription Summarizer"
description = "Enter a YouTube Video URL to get a summary of its transcript."

iface = gr.Interface(fn=summarize_video_url, inputs=input, outputs=output, title=title, description=description)

iface.launch(share=True)