Update app.py

app.py

@@ -12,11 +12,17 @@ import IPython.display as ipd
 image_to_text_model = pipeline("image-classification")
 text_to_audio_model = pipeline("text-to-speech")
 
-
+def image_to_texto(input_image):
+    # Convertir la imagen a texto
+    text_output = image_to_text_model(input_image)[0]['label']
+    print('text_output is :'+text_output)
+    
+    return text_output
+    
 # Función para la interfaz de Gradio
 def image_to_audio(input_image):
     # Convertir la imagen a texto
-    text_output = image_to_text_model(input_image)[0]['label']
+    text_output = image_to_texto(input_image)[0]['label']
     print('text_output is :'+text_output)
     # Generar audio a partir del texto
     audio_output = text_to_audio_model(text_output)[0]['audio']
@@ -27,7 +33,7 @@ def image_to_audio(input_image):
 iface = gr.Interface(
     fn=image_to_audio,
     inputs=gr.Image(type='pil'),
-    outputs=[gr.Textbox(value=image_to_text_model, label="Output"), gr.Audio()],
+    outputs=[gr.Textbox(), gr.Audio()],
     live=True,
     interpretation="default",
     capture_session=True