app.py

from pytube import YouTube
from transformers import pipeline
import gradio as gr
import os

model = pipeline(model="renesteeman/whisper-base-dutch-25")

def get_audio(url):
  yt = YouTube(url)
  video = yt.streams.filter(only_audio=True).first()
  out_file=video.download(output_path=".")
  base, ext = os.path.splitext(out_file)
  new_file = base+'.mp3'
  os.rename(out_file, new_file)
  a = new_file
  return a

def get_text(url):
#   result = model.transcribe(get_audio(url))
#   return result['text'].strip()
    text = model(get_audio(url))["text"]
    return text

# For Local usage
# print(get_text("https://www.youtube.com/shorts/KvgkcQMCq44"))

iface = gr.Interface(
    fn=get_text, 
    inputs="text", 
    outputs="text",
    title="Whisper Small Dutch",
    description="Realtime demo for Dutch speech recognition using a fine-tuned Whisper small model.",
)

iface.launch()