app.py

import gradio as gr
import whisper
import os

# Load the Whisper model
model = whisper.load_model("base")  # Choose 'tiny', 'base', 'small', 'medium', or 'large'

def write_srt(transcription, output_file):
    with open(output_file, "w") as f:
        for i, segment in enumerate(transcription['segments']):
            start = segment['start']
            end = segment['end']
            text = segment['text']
            # Format timestamps for SRT
            start_time = whisper.utils.format_timestamp(start)
            end_time = whisper.utils.format_timestamp(end)
            print(f"Writing subtitle {i + 1}: {text.strip()} ({start_time} --> {end_time})")  # Debug print
            f.write(f"{i + 1}\n")
            f.write(f"{start_time} --> {end_time}\n")
            f.write(f"{text.strip()}\n\n")

def transcribe_video(video_file):
    # Transcribe the video to generate subtitles
    result = model.transcribe(video_file)
    
    # Save the transcription to an .srt file
    srt_file = "generated_subtitles.srt"
    
    # Write the transcription as subtitles
    write_srt(result, srt_file)
    
    return srt_file

# Gradio interface
iface = gr.Interface(
    fn=transcribe_video,
    inputs=gr.File(label="Upload Video"),
    outputs=gr.File(label="Download Subtitles"),
    title="Video Subtitle Generator",
    description="Upload a video file to generate subtitles using Whisper."
)

if __name__ == "__main__":
    iface.launch()