app.py

import gradio as gr 
import os
import sys
import subprocess


import whisper


model = whisper.load_model("medium")

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)
    model = whisper.load_model("base")
  
    audio = whisper.load_audio(audio_file)
    #result= model.transcribe(audio)
    
    options = dict(beam_size=5, best_of=5)
    translate_options = dict(task="translate", **options)
    transcribe_options = dict(task="transcribe", **options)
    result_translate = model.transcribe(audio_file,**translate_options)
    result_transcribe = model.transcribe(audio_file,**transcribe_options)
    
    return "Transcribe result :"+result_transcribe["text"]  +"\n ---Translated text in english ---- "+result_translate["text"]
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.Textbox()
            btn = gr.Button("Generate Subtitle Video")
        
        
        


        
        btn.click(translate, inputs=[inp_video], outputs=[op_video],api_name="view_api")
block.launch(enable_queue = True,debug=True)