“Zhiyong Zhang 2016-05-09”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(相同用户的2个中间修订版本未显示)
第1行: 第1行:
 
*Weekly Report
 
*Weekly Report
# 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
 
 
# Investigate the Reranker Framework(ReFr) toolkit for discriminative language model training
 
# Investigate the Reranker Framework(ReFr) toolkit for discriminative language model training
 +
# 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
 
*To do next week
 
# Try to use ReFr to train a discriminative language model
 
# Try to use ReFr to train a discriminative language model

2016年5月9日 (一) 00:51的最后版本

  • 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