Update app.py

app.py

@@ -9,8 +9,9 @@ emotion_labels = {0: 'neutral', 1: 'calm', 2: 'happy', 3: 'sad', 4: 'angry', 5:
 
 def process_video_audio(video_path, audio_path):
 
-    wav = np.array(audio_path[1])
-    wav = pt.tensor(wav)
+    wav = pt.stack(list(audio_path[1]), dim=0)
+
+    print(wav.shape)
     
     train_visual = np.zeros([1, 120, 120, 3, 10])
     train_audio_wave = np.zeros([1, 261540])