app.py

import gradio as gr
from transformers import pipeline

asr_model = pipeline("automatic-speech-recognition", model="openai/whisper-small")
def transcribe(audio_file):
    transcription = asr_model(audio_file)
    return transcription["text"]

iface = gr.Interface(
    fn=transcribe,
    inputs=gr.inputs.Audio(source="microphone", type="filepath"),
    outputs="text"
)

iface.launch()