app.py

import gradio as gr
from transformers import pipeline

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

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

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

demo = gr.Blocks()

with demo:
  gr.Markdown("Este es el segundo demo con Blocks")
  with gr.Tabs():
    with gr.TabItem("Transcribe audio en español"):
      with gr.Row():
        audio = gr.Audio(source="microphone", type="filepath")
        transcripcion = gr.Textbox()
      b1 = gr.Button("Transcribe porfa")
    
    with gr.TabItem("Análisis de sentimiento en español"):
      with gr.Row():
        texto = gr.Textbox()
        label = gr.Label()
      b2 = gr.Button("sentimiento porfa")
    
    


    b1.click(audio_a_text, inputs = audio, outputs = transcripcion)
    b2.click(texto_a_sentimiento, inputs = texto, outputs = label)
    #b3.click(clasifica_imagen, inputs = imagen, outputs=label1)


demo.launch()