“Zhiyong Zhang 2016-05-09”版本间的差异
来自cslt Wiki
| 第3行： | 第3行： | ||
:# WER17.99 for 1e-7(size:13M) lm-threshold | :# WER17.99 for 1e-7(size:13M) lm-threshold | ||
:# WER17.51 for 1e-8(size:54M) 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 | ||
2016年5月9日 (一) 00:50的版本
- 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
- To do next week
- Try to use ReFr to train a discriminative language model
