diff --git a/download_dataset.sh b/download_dataset.sh
new file mode 100644
index 0000000..d2a9361
--- /dev/null
+++ b/download_dataset.sh
@@ -0,0 +1,4 @@
+#!/bin/sh
+wget http://svn.code.sf.net/p/cmusphinx/code/trunk/cmudict/cmudict-0.7b
+wget http://svn.code.sf.net/p/cmusphinx/code/trunk/cmudict/scripts/make_baseform.pl
+perl make_baseform.pl cmudict-0.7b cmudict-0.7b_baseform
\ No newline at end of file