“Mengyuan Zhao 2015-12-07”版本间的差异
来自cslt Wiki
（以“==== RNN AM==== *AM training on big dataset --mengyuan :* fix decode bug :* nnet3 lstm training on sinovoice 120h dataset, using KALDI's default config.”为内容创建页面） |
|||
| 第2行： | 第2行： | ||
*AM training on big dataset --mengyuan | *AM training on big dataset --mengyuan | ||
:* fix decode bug | :* fix decode bug | ||
| − | :* nnet3 lstm training on sinovoice 120h dataset, using KALDI's default config. | + | :* nnet3 lstm & blstm training on sinovoice 120h dataset, using KALDI's default config. but result is worse than tdnn |
2015年12月7日 (一) 05:12的最后版本
RNN AM
- AM training on big dataset --mengyuan
- fix decode bug
- nnet3 lstm & blstm training on sinovoice 120h dataset, using KALDI's default config. but result is worse than tdnn
