app.py

import gradio as gr
from transformers import pipeline
p = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-base-960h")

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

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