app.py

import gradio as gr
import time
def transcribe (audio, state=" "):
    time.sleep(3)
    """ speech to text function using the pipeline that we defined"""
    text= p(audio) ["text"]
    state += text + " "
    return state, state
gr.Interface(
    fn=transcribe,
    inputs=[
           gr.inputs.Audio(source="microphone", type="filepath"),
            "state"
    ],
    outputs=[
             "textbox",
             "state"
    ],
    live=True).launch()