Specified the test set.

v1vekkumar · Oct 14, 2016 · 680d04d · 680d04d
1 parent 22bd5aa
commit 680d04d
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -28,7 +28,8 @@ A simple class that provides an easy to use API to access the data.
 `spectogramer.py`
 Used for creating spectrograms of the audio data. Spectrograms are often a useful pre-processing step.
 
-
+### Usage
+The test set officially consists of the first 10% of the recordings. Recordings numbered `0-4` (inclusive) are in the test and `5-49` are in the training set. 
 
 ### Contributions
 Please contribute your homemade recordings. All recordings should be 8kHz `wav ` files and be trimmed to have minimal silence. Don't forget to update `metadata.py` with the speaker meta-data.
diff --git a/utils/fsdd.py b/utils/fsdd.py
@@ -1,7 +1,5 @@
 import os
 from collections import defaultdict
-import PIL
-import numpy as np
 import scipy.io.wavfile
 import scipy.ndimage