app.py

import gradio as gr
from transformers import pipeline


model = pipeline(task="automatic-speech-recognition",
gr.Interface.load("models/facebook/s2t-medium-librispeech-asr")               


def predict_speech_to_text(audio):
    prediction = model(audio)
    text = prediction['text']
    return text


gr.Interface(fn=predict_speech_to_text,
             title="🧑🏽‍🎤 PROLOVE 🥰😘 ",
             inputs=gr.inputs.Audio(
                 source="microphone", type="filepath", label="Input"),
             outputs=gr.outputs.Textbox(label="Output"),
             description="This application was created to help correct pronouncation",
             examples=['Good night_alvi.wav'],
             allow_flagging='never'
             ).launch(share=True)