Update app.py

app.py

@@ -9,8 +9,9 @@ audio_gen = gr.Blocks.load(name="spaces/haoheliu/audioldm-text-to-audio-generati
 def infer(image_input):
     cap = caption(image_input, fn_index=0)
     sound = audio_gen(cap, 10, 2.5, 45, 3, fn_index=0)
-    time.sleep(2)
+    
     FILETOCONVERT = AudioFileClip(sound)
+    time.sleep(2)
     FILETOCONVERT.write_audiofile("audio.wav")
     FILETOCONVERT.close()
     return gr.Textbox.update(value=cap, visible=True), "audio.wav", gr.Group.update(visible=True)