fix ds2 configs

docs/src/text_front_end.md

@@ -0,0 +1,15 @@
+# Text Front End
+
+## MMSEG
+* [MMSEG: A Word Identification System for Mandarin Chinese Text Based on Two Variants of the Maximum Matching Algorithm](http://technology.chtsai.org/mmseg/)
+* [`中文分词`简单高效的MMSeg](https://www.cnblogs.com/en-heng/p/5872308.html)
+* [mmseg分词算法及实现](https://blog.csdn.net/daniel_ustc/article/details/50488040)
+* [Mmseg算法](https://www.jianshu.com/p/e4ae8d194487)
+* [浅谈中文分词](http://www.isnowfy.com/introduction-to-chinese-segmentation/)
+
+* [ustcdane/mmseg](https://github.com/ustcdane/mmseg)
+* [jkom-cloud/mmseg](https://github.com/jkom-cloud/mmseg)
+
+
+## CScanner
+* [CScanner - A Chinese Lexical Scanner](http://technology.chtsai.org/cscanner/)

examples/aishell/s0/.gitignore

@@ -0,0 +1,3 @@
+exp
+data
+*log

examples/aishell/s0/conf/deepspeech2.yaml

@@ -3,7 +3,7 @@ data:
   train_manifest: data/manifest.train
   dev_manifest: data/manifest.dev
   test_manifest: data/manifest.test
-  mean_std_filepath: data/mean_std.npz
+  mean_std_filepath: data/mean_std.json
   vocab_filepath: data/vocab.txt 
   augmentation_config: conf/augmentation.json
   batch_size: 64 # one gpu

examples/librispeech/s0/conf/deepspeech2.yaml

@@ -3,7 +3,7 @@ data:
   train_manifest: data/manifest.train
   dev_manifest: data/manifest.dev-clean
   test_manifest: data/manifest.test-clean
-  mean_std_filepath: data/mean_std.npz
+  mean_std_filepath: data/mean_std.json
   vocab_filepath: data/vocab.txt 
   augmentation_config: conf/augmentation.json
   batch_size: 20