app.py

import os
import numpy as np
import gradio as gr
import whisper

model = whisper.load_model("base.en")

def fun(audio, state=''):
  text = model.transcribe(audio)["text"]
  state += text + " "
  return state, state
  
def transcribe(audio, state=""):
    text = p(audio)["text"]
    state += text + " "
    return state, state

# Set the starting state to an empty string

#gr.Interface(
#    fn=transcribe, 
#    inputs=[
#        gr.Audio(source="microphone", type="filepath", streaming=True), 
#        "state" 
#    ],
#    outputs=[
#        "textbox",
#        "state"
#    ],
#    live=True).launch()
    
    
gr.Interface(
    title = 'Testing Whisper', 
    fn=fun, 
    inputs=[
        gr.inputs.Audio(source="microphone", streaming = True, type="filepath"),
        "state"
    ],
    outputs=[
        "textbox", "state"
    ],
    live=True).launch()