app.py

from transformers import pipeline
import gradio as gr

pipe = pipeline(model="asif00/whisper-bangla")


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


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

iface.launch()