app.py

from transformers import pipeline
import gradio as gr

p = pipeline("automatic-speech-recognition", model = "jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn")

def transcribe(audio, state=""):
    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()