Update app.py

app.py

@@ -13,7 +13,8 @@ def generate_captions_speech(image):
 
     caption_blip_large = itm.generate_caption(itm.blip_processor_large, itm.blip_model_large, image)
     print('generate_captions>>>'+caption_blip_large)
-    return caption_blip_large,am.synthesize_speech(caption_blip_large)
+    speech=amsynthesize_speech(caption_blip_large)
+    return caption_blip_large,gr.Audio.update(value=(16000, speech.cpu().numpy()))
     
     
 # Define la interfaz de usuario utilizando Gradio entradas y salidas