app.py

import speech_recognition as sr
from httpcore import SyncHTTPProxy
from googletrans import Translator

"""
http_proxy = SyncHTTPProxy((b'http', b'myproxy.com', 8080, b''))
proxies = {'http': http_proxy, 'https': http_proxy }

def transcribeHindi():
         
    r = sr.Recognizer()
    with sr.Microphone() as source:
          
        # seconds of non-speaking audio before 
        # a phrase is considered complete
        print('Listening')
        r.pause_threshold = 0.7  
        audio = r.listen(source)  
        try:
            print("Recognizing")
            Query = r.recognize_google(audio, language='hi-In')
              
            # for listening the command in indian english
            print("the query is printed='", Query, "'")
          
        # handling the exception, so that assistant can 
        # ask for telling again the command
        except Exception as e:
            print(e)  
            print("Say that again sir")
            return "None"
        return Query

def translate():
    query = transcribeHindi()
    translator = Translator()
    translation = translator.translate(query, dest='en')
    return translation.text

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

gr.Interface(
    fn=transcribe, 
    inputs=gr.Audio(source="microphone", type="filepath"), 
    outputs="text").launch()