app.py

import gradio as gr
from transformers import pipeline

modelo = pipeline('automatic-speech-recognition', model = 'facebook/wav2vec2-large-xlsr-53-spanish')
titulo = "Audio2Text"
descripcion = "Graba un audio en castellano y envíalo para obtener la transcripción"


def transcribe(audio):
  text = modelo(audio)['text']
  return text

gr.Interface(
    fn = transcribe,
    inputs = gr.Audio(source = 'microphone', type = 'filepath'),
    outputs = ['textbox'],
    title = titulo,
    description = descripcion
).launch()