app.py

from transformers import pipeline
import gradio as gr
import time

p = pipeline("automatic-speech-recognition", model="indonesian-nlp/wav2vec2-indonesian-javanese-sundanese")

def transcribe(audio, state=""):
    time.sleep(2)
    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()