app.py

import gradio as gr
import torchaudio

def transcribe(audio):
    recognizer = sr.Recognizer()
    with sr.AudioFile(audio) as source:
        audio_data = recognizer.record(source)
        text = recognizer.recognize_google(audio_data, language="fa-IR")
        return text

interface = gr.Interface(fn=transcribe, inputs="microphone", outputs="text")
interface.launch()