Update app.py

app.py

@@ -43,9 +43,10 @@ def text_to_audio_file(text):
 # Gradio interface: Caption + Audio
 # -------------------------------
 def generate_caption_tts(image):
-    caption = generate_caption_tts(model, processor, image)
+    caption = generate_caption_from_image(model, processor, image)  # uses global model/processor
     audio_file = text_to_audio_file(caption)
-    return caption, audio_file  # return file path, not BytesIO
+    return caption, audio_file
+
 
 
 interface = gr.Interface(