Zhiyong Zhang 2016-05-09

来自cslt Wiki
跳转至: 导航搜索
  • Weekly Report
  1. Investigate the Reranker Framework(ReFr) toolkit for discriminative language model training
  2. Test character-lm with word-boundary
  • WER17.99 for 1e-7(size:13M) lm-threshold
  • WER17.51 for 1e-8(size:54M) lm-threshold
  • All worse than character-lm without boundary which is WER13.24 (size:71M) lm-threshold:1e-7
  • To do next week
  1. Try to use ReFr to train a discriminative language model