pipe = pipeline(model = "suvrobaner/whisper-small-finetuned-hi-commonvoice")

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

iface = gr.Interface(
    fn=transcribe, 
    inputs=gr.Audio(source="microphone", type="filepath"), 
    outputs="text",
    title="Whisper Small Hindi Transcribe",
    description="Realtime demo for Hindi speech recognition using a fine-tuned Whisper small model on Common Voice dataset.",
)

iface.launch()