app.py

import gradio as gr 
import os
import sys
import subprocess
#from moviepy.editor import VideoFileClip

import whisper
from whisper.utils import write_vtt

model = whisper.load_model("medium")

title = "Add Text/Caption to your YouTube Shorts - MultiLingual"

def video2mp3(video_file, output_ext="mp3"):
    filename, ext = os.path.splitext(video_file)
    subprocess.call(["ffmpeg", "-y", "-i", video_file, f"{filename}.{output_ext}"], 
                    stdout=subprocess.DEVNULL,
                    stderr=subprocess.STDOUT)
    return f"{filename}.{output_ext}"


def translate(input_video):

    audio_file = video2mp3(input_video)
    
    options = dict(beam_size=5, best_of=5, fp16 = False)
    translate_options = dict(task="translate", **options)
    result = model.transcribe(audio_file,**translate_options)

    output_dir = ''
    
    with open(os.path.join(output_dir, 'audio' + ".vtt"), "w") as vtt:
      write_vtt(result["segments"], file=vtt)

    subtitle     = "subtitles.vtt"
    output_video = "subtitled.mp4"

    os.system(f"ffmpeg -i {input_video} -vf subtitles={subtitle} {output_video}")

    return output_video

block = gr.Blocks()
with block:

    with gr.Group():
        with gr.Box():
            with gr.Row().style():
                inp_video = gr.Video(
                    label="Input Video",
                    type="filepath",
                    mirror_webcam = False
                )
                op_video = gr.Video()
            btn = gr.Button("Generate Subtitle Video")
        
        
        


        
        btn.click(translate, inputs=[inp_video], outputs=[op_video])

block.launch(enable_queue = True)