diff --git a/beginner_source/audio_preprocessing_tutorial.py b/beginner_source/audio_preprocessing_tutorial.py
index fea8d3d5a88..01c5a4a748a 100644
--- a/beginner_source/audio_preprocessing_tutorial.py
+++ b/beginner_source/audio_preprocessing_tutorial.py
@@ -213,7 +213,7 @@ def normalize(tensor):
 # Now let's experiment with a few of the other functionals and visualize their output. Taking our 
 # spectogram, we can compute it's deltas:
 
-computed = torchaudio.functional.compute_deltas(specgram, win_length=3)
+computed = torchaudio.functional.compute_deltas(specgram.contiguous(), win_length=3)
 print("Shape of computed deltas: {}".format(computed.shape))
 
 plt.figure()