Update app.py

app.py

@@ -43,7 +43,7 @@ def text_to_audio_file(text):
 # Gradio interface: Caption + Audio
 # -------------------------------
 def generate_caption_tts(image):
-    caption = generate_caption(model, processor, image)
+    caption = generate_caption_tts(model, processor, image)
     audio_file = text_to_audio_file(caption)
     return caption, audio_file  # return file path, not BytesIO