app.py

import gradio as gr
import os
import subprocess
from transformers import pipeline
from langdetect import detect

def download_audio(youtube_url):
    output_file = "audio.mp3"
    # Remove old file if exists
    if os.path.exists(output_file):
        os.remove(output_file)
    cmd = [
        "yt-dlp", "-x", "--audio-format", "mp3", "-o", output_file, youtube_url
    ]
    subprocess.run(cmd, check=True)
    return output_file

def process_youtube(youtube_url):
    try:
        audio_path = download_audio(youtube_url)
    except Exception as e:
        return "Error downloading audio: " + str(e), "", "", ""
    try:
        asr = pipeline("automatic-speech-recognition", model="openai/whisper-large")
        result = asr(audio_path)
        transcript = result["text"]
    except Exception as e:
        return "Error in transcription: " + str(e), "", "", ""
    try:
        detected_lang = detect(transcript)
    except Exception:
        detected_lang = "unknown"
    lang_map = {'en': 'English', 'hi': 'Hindi', 'ta': 'Tamil'}
    lang_text = lang_map.get(detected_lang, detected_lang)
    transcript_en = transcript
    if detected_lang != "en":
        try:
            asr_translate = pipeline(
                "automatic-speech-recognition",
                model="openai/whisper-large",
                task="translate"
            )
            result_translate = asr_translate(audio_path)
            transcript_en = result_translate["text"]
        except Exception as e:
            transcript_en = f"Error translating: {e}"
    try:
        summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
        summary = summarizer(transcript_en, max_length=100, min_length=30, do_sample=False)
        summary_text = summary[0]["summary_text"]
    except Exception as e:
        summary_text = f"Error summarizing: {e}"
    if os.path.exists(audio_path):
        os.remove(audio_path)
    return lang_text, transcript, transcript_en, summary_text

with gr.Blocks() as demo:
    gr.Markdown("## YouTube Transcript, Translation & Summary (Powered by Whisper + Hugging Face)")
    url_input = gr.Textbox(label="YouTube URL")
    btn = gr.Button("Process")
    lang_out = gr.Textbox(label="Detected Language")
    transcript_out = gr.Textbox(label="Original Transcript")
    transcript_en_out = gr.Textbox(label="English Transcript (if translated)")
    summary_out = gr.Textbox(label="Summary")
    btn.click(
        process_youtube,
        inputs=[url_input],
        outputs=[lang_out, transcript_out, transcript_en_out, summary_out]
    )

demo.launch()