app.py

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

asr = pipeline("automatic-speech-recognition", model="openai/whisper-small")
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")

def process_audio(audio_path):
    if not audio_path or isinstance(audio_path, bool):
        return "No audio file provided.", "", "", ""
    try:
        result = asr(audio_path)
        transcript = result["text"]
    except Exception as e:
        return f"Error in transcription: {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:
            result_translate = asr(audio_path, generate_kwargs={"task": "translate"})
            transcript_en = result_translate["text"]
        except Exception as e:
            transcript_en = f"Error translating: {e}"
    try:
        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}"
    return lang_text, transcript, transcript_en, summary_text

iface = gr.Interface(
    fn=process_audio,
    inputs=gr.Audio(source="upload", type="filepath", label="Upload MP3/WAV Audio"),
    outputs=[
        gr.Textbox(label="Detected Language"),
        gr.Textbox(label="Original Transcript"),
        gr.Textbox(label="English Transcript (if translated)"),
        gr.Textbox(label="Summary"),
    ],
    title="Audio Transcript, Translation & Summary",
    description="Upload your audio file (MP3/WAV). This app transcribes, detects language, translates to English if needed, and summarizes."
)

iface.launch()