app.py

import gradio as gr
from transformers import pipeline


inputs=gr.Audio(type="filepath")
pipe = pipeline(model="TruongScotl/stvi")
title = "Speech to Text Translation"
description = """
<p>
<center>
Open your eyes Morty, that translator is mind-blowing. Drop the damn file, Morty!
<img src="https://huggingface.co/spaces/course-demos/Rick_and_Morty_QA/resolve/main/rick.png" width=200px>
</center>
</p>
"""

def translate(audio):
    text = pipe(audio)["text"]
    return text

translate = gr.Interface(
    fn=translate,
    inputs=inputs,
    outputs="text",
    title=title,
    description=description
)

translate.launch()