delay user audio decoding

app.py

@@ -1,3 +1,4 @@
+import time
 import torch
 import spaces
 import numpy as np
@@ -54,6 +55,7 @@ def generate(instruct_history, temperature=0.1, max_new_tokens=128, top_p=0.95,
 def transcribe(audio, past_history):
     global instruct_history, formatted_history
 
+    time.sleep(1)
     sr, y = audio
     y = y.astype(np.float32)
     y /= np.max(np.abs(y))