from transformers import pipeline
p = pipeline("automatic-speech-recognition")
import gradio as gr
import time
def transcribe(audio, state=""):
    time.sleep(3)
    text = p(audio)["text"]
    state += text + " "
    return state, state
   
    
 # embedded 'Record' may not work hence use 'https://39357.gradio.app'. In an external browser, speak and you will get the text output
ST_ASR_demo = gr.Interface(
    fn=transcribe, 
    inputs=[
        gr.inputs.Audio(source="microphone", type="filepath"),
        'state'
    ],
    outputs=[
        "textbox",
        "state"
    ],
    title = 'Real-Time Speech Transcription', description = 'Speak something, you will get the text as an output',
    live=True)#.launch(inline = False)