segunda correcion

app.py

@@ -1,33 +1,3 @@
-import tensorflow as tf
-
-inception_net = tf.keras.applications.MobileNetV2()
-
-import requests
-
-respuesta  = requests.get("https://git.io/JJkYN")
-etiquetas = respuesta.text.split("\n")
-# Obteniendo las labels de "https://git.io/JJkYN"
-
-def clasifica_imagen(inp):
-  inp = inp.reshape((-1,224,224,3))
-  inp = tf.keras.applications.mobilenet_v2.preprocess_input(inp)
-  prediction = inception_net.predict(inp).flatten()
-  confidences = {etiquetas[i]: float(prediction[i]) for i in range(1000)}
-  return confidences
-
-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()
 
@@ -46,16 +16,12 @@ with demo:
         label = gr.Label()
       b2 = gr.Button("sentimiento porfa")
     
-    with gr.TabItem("Clasificacion de imagenes"):
-      with gr.Row():
-        imagen = gr.Image(shape=(224,224))
-        label1 = gr.Label(num_top_classes=3)
-      b3 = gr.Button("clasifica")
+    
 
 
     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)
+    #b3.click(clasifica_imagen, inputs = imagen, outputs=label1)
 
 
 demo.launch()