diff --git a/README.md b/README.md
index 7faf60c..8ebb9e9 100644
--- a/README.md
+++ b/README.md
@@ -7,4 +7,5 @@ Download pretrained model and dataset from https://github.com/gheyret/uyghur-asr
 unzip results.7z and thuyg20_data.7z to the same folder where python source files located.
 
 
-Using Thuyg20 dataset.
+This project using 
+A free Uyghur speech database Released by CSLT@Tsinghua University & Xinjiang University(http://www.openslr.org/22/)