app.py

from transformers import pipeline
import gradio as gr

p = pipeline("automatic-speech-recognition")

def transcribe(audio, state=""):
  """ Speech to text function using pipeline"""
  text = p(audio)["text"]
  state += text + " "
  return state, state
  
 gr.Interface(fn=transcribe, inputs=[gr.inputs.Audio(source="microphone", type="filepath", label="Record/ Drop audio"), "state"],
     outputs=["textbox", "state"],
     title="Automatic Speech Recognition",
     description="Enable the recognition spoken language into text by computers.",
     theme="huggingface",
     live=True).launch()