app.py

import gradio as gr
import os
from moviepy.editor import VideoFileClip
from transformers import pipeline

# Load ASR (Speech-to-Text) pipeline
asr = pipeline(task="automatic-speech-recognition", model="distil-whisper/distil-small.en")

# Load Summarization model
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")

def transcribe_and_summarize(video_file):
    if video_file is None:
        return "Error: No file provided.", ""

    try:
        # Extract audio from the video file
        video = VideoFileClip(video_file)
        audio_path = "temp_audio.wav"
        video.audio.write_audiofile(audio_path, codec='pcm_s16le')

        # Transcribe the extracted audio
        transcription_result = asr(audio_path, return_timestamps=True)
        transcribed_text = " ".join([segment['text'] for segment in transcription_result['chunks']])

        # Summarize if long enough
        if len(transcribed_text.split()) < 50:
            summarized_text = "Text too short to summarize."
        else:
            summary_result = summarizer(transcribed_text, max_length=100, min_length=30, do_sample=False)
            summarized_text = summary_result[0]['summary_text']

        return transcribed_text, summarized_text

    except Exception as e:
        return f"Error: {str(e)}", ""

# Create Gradio interface
iface = gr.Interface(
    fn=transcribe_and_summarize,
    inputs=gr.Video(type="filepath", label="Upload Video (.mp4)"),
    outputs=[
        gr.Textbox(label="Transcribed Text"),
        gr.Textbox(label="Summarized Text")
    ]
)

# Launch app
port = int(os.environ.get('PORT1', 7860))
iface.launch(share=True, server_port=port)