“Mengyuan Zhao 2015-12-14”版本间的差异
来自cslt Wiki
（以“==== RNN AM==== *AM training on big dataset --mengyuan :* Test nnet3-MPE code from Xuewei on sinovoice 120h 16k dataset. Didn't observe performance improvement. Ther...”为内容创建页面） |
|||
| 第3行： | 第3行： | ||
:* Test nnet3-MPE code from Xuewei on sinovoice 120h 16k dataset. Didn't observe performance improvement. There are still some bugs in the code. | :* Test nnet3-MPE code from Xuewei on sinovoice 120h 16k dataset. Didn't observe performance improvement. There are still some bugs in the code. | ||
:* Run nnet3-ctc training on sinovoice 120h 16k dataset. Result looks ok, but worse normal model. | :* Run nnet3-ctc training on sinovoice 120h 16k dataset. Result looks ok, but worse normal model. | ||
| − | + | :* Start nnet3-ctc training on sinovoice 4000h 8k dataset. | |
2015年12月13日 (日) 12:44的版本
RNN AM
- AM training on big dataset --mengyuan
- Test nnet3-MPE code from Xuewei on sinovoice 120h 16k dataset. Didn't observe performance improvement. There are still some bugs in the code.
- Run nnet3-ctc training on sinovoice 120h 16k dataset. Result looks ok, but worse normal model.
- Start nnet3-ctc training on sinovoice 4000h 8k dataset.
