Update app.py

app.py

@@ -11,8 +11,10 @@ audio_gen = gr.Blocks.load(name="spaces/fffiloni/audioldm-text-to-audio-generati
 def infer(image_input, manual_caption):
     if manual_caption == None:
         cap = caption(image_input, fn_index=0)
+        print("gpt2 caption: " + cap)
     else:
         cap = manual_caption
+        print("manual caption: " + cap)
     sound = audio_gen(cap, 10, 2.5, 45, 3, fn_index=0)
     
     return cap, sound[1], gr.Group.update(visible=True)