Update app.py

app.py

@@ -3,17 +3,17 @@ from transformers import AutoProcessor, BlipForConditionalGeneration, AutoTokeni
 import librosa
 import numpy as np
 import torch
-import image_text_model
-import audio_model
+import image_text_model as itm
+import audio_model as am 
 import open_clip
 
 #CONSTANTS
 
 def generate_captions_speech(image):
 
-    caption_blip_large = generate_caption(blip_processor_large, blip_model_large, image)
+    caption_blip_large = itm.generate_caption(blip_processor_large, blip_model_large, image)
     print('generate_captions>>>'+caption_blip_large)
-    return caption_blip_large,text_to_speech(caption_blip_large,"Surprise Me!")
+    return caption_blip_large,am.text_to_speech(caption_blip_large,"Surprise Me!")
     
     
 # Define la interfaz de usuario utilizando Gradio entradas y salidas