app.py

from transformers import pipeline
import gradio as gr

model = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-large-xlsr-53-spanish")
def transcribe(audio):
  texto = model(audio)["text"]
  return texto

app = gr.Interface(fn=transcribe, inputs=gr.Audio(sources=["microphone"], type="filepath", label="Record Audio"), outputs=["textbox"])
app.launch()