app.py

import gradio as gr
from transformers import pipeline

p = pipeline('speech-to-text', model='wannaphong/wav2vec2-large-xlsr-53-th-cv8-deepcut')

def transcribe(audio):
    text = p(audio)["text"]
    return text
    
gr.Interface(
    fn=transcribe, 
    inputs=gr.Audio(source="microphone", type="filepath"), 
    outputs="text").launch()