“Zhiyong Zhang 2016-04-18”版本间的差异
来自cslt Wiki
（以“*Weekly report # Character-LM and Word-LM merge :# Union the two can achieve 9.53-wer compared with only word-LM 9.67-wer, but the HCLG is twice bigger than only wor...”为内容创建页面） |
|||
| 第1行： | 第1行： | ||
*Weekly report | *Weekly report | ||
# Character-LM and Word-LM merge | # Character-LM and Word-LM merge | ||
| − | :# Union the two can achieve 9.53-wer compared with only word-LM 9.67-wer, but the HCLG is twice bigger than only word-lm; | + | :# Union the two can achieve 9.53-wer compared with only word-LM 9.67-wer, but the HCLG is twice bigger than only word-lm; |
| − | :# Compose get an wer of 64-wer, need deep investigation | + | :# Compose get an wer of 64-wer, need deep investigation |
| + | |||
# Re-compile nnet3-mpe under the 20160410 kaldi version | # Re-compile nnet3-mpe under the 20160410 kaldi version | ||
# Assist the restaurant recording of Siason | # Assist the restaurant recording of Siason | ||
2016年4月18日 (一) 00:52的版本
- Weekly report
- Character-LM and Word-LM merge
:# Union the two can achieve 9.53-wer compared with only word-LM 9.67-wer, but the HCLG is twice bigger than only word-lm; :# Compose get an wer of 64-wer, need deep investigation
- Re-compile nnet3-mpe under the 20160410 kaldi version
- Assist the restaurant recording of Siason
- Assist the implementation of NG-SGD in nnet1 version with Xiangyu
- Next week
- To solve the deletion error in discriminative training
- To check the SVD re-train failure problem
