Update app.py

app.py

@@ -10,6 +10,7 @@ from transformers import AutoConfig, AutoModel, Wav2Vec2FeatureExtractor
 import librosa
 import numpy as np
 import subprocess
+import time
 
 TRUST = True
 SR = 16000
@@ -46,9 +47,9 @@ print(device)
 
 
 def recognize(audio, state={}):
+    time.sleep(2)
     sr, audio_array = audio
     audio_array = audio_array.astype(np.float32)
-    print(sr, audio_array)
     state = predict(audio_array, sr)
     return state, state