Update README.md
Browse files
README.md
CHANGED
|
@@ -23,6 +23,8 @@ z = model('path/audio_fname.wav') # (768, 8, 64) = (latent_dim_size, latent_fre
|
|
| 23 |
Depending on a task, a different pooling strategy should be facilitated.
|
| 24 |
For instance, a global average pooling can be used for a classification task. [2] uses an adaptive pooling.
|
| 25 |
|
|
|
|
|
|
|
| 26 |
|
| 27 |
# Sanity Check Result
|
| 28 |
In the following, a spectrogram of an input audio and corresponding $z$ are visualized.
|
|
|
|
| 23 |
Depending on a task, a different pooling strategy should be facilitated.
|
| 24 |
For instance, a global average pooling can be used for a classification task. [2] uses an adaptive pooling.
|
| 25 |
|
| 26 |
+
⚠️ AudioMAE accepts audio with maximum length of 10s (as described in [1]). Any audio longer than 10s will be clipped to 10s, meaning the excess beyond 10s will be discarded.
|
| 27 |
+
|
| 28 |
|
| 29 |
# Sanity Check Result
|
| 30 |
In the following, a spectrogram of an input audio and corresponding $z$ are visualized.
|