Mengyuan Zhao 2015-12-14

来自cslt Wiki
2015年12月13日 (日) 12:44Zhaomy讨论 | 贡献的版本

(差异) ←上一版本 | 最后版本 (差异) | 下一版本→ (差异)
跳转至: 导航搜索

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 than normal model.
  • Start nnet3-ctc training on sinovoice 4000h 8k dataset.