app.py

from transformers import pipeline
import gradio as gr

pipe = pipeline(
    model="anggiatm/whisper-small-id"
)  # change to "your-username/the-name-you-picked"


def transcribe(audio):
    text = pipe(audio)["text"]
    return text


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

iface.launch()