app.py

import gradio as gr
from transformers import pipeline

trans = pipeline("automatic-speech-recognition", "facebook/wav2vec2-large-xlsr-53-spanish")
clasificador = pipeline("text-classification", model = "pysentimiento/robertuito-sentiment-analysis")

def audio_a_texto(audio):
  text = trans(audio)["text"]
  return text

def texto_a_sentimiento(text):
  return clasificador(text)[0]["label"]

demo = gr.Blocks()

with demo:
  gr.Markdown("Demo")
  audio = gr.Audio(source = "microphone", type = "filepath")
  texto = gr.Textbox()
  b1 = gr.Button("Transcribe!")
  b1.click(
    fn = audio_a_texto,
    inputs = audio,
    outputs = texto
  )

  label = gr.Label()
  b2 = gr.Button("Clasify!")
  b2.click(
    fn = texto_a_sentimiento,
    inputs = texto,
    outputs = label
  )

demo.launch()