“2013-04-26”版本间的差异
来自cslt Wiki
| 第45行： | 第45行： | ||
===GPU & CPU merge=== | ===GPU & CPU merge=== | ||
| − | : Invesigate the possibility to merge GPU and CPU code. | + | : Invesigate the possibility to merge GPU and CPU code. GPU computing code merged to CPU. |
===L-1 sparse initial training=== | ===L-1 sparse initial training=== | ||
| 第51行： | 第51行： | ||
==Kaldi/HTK merge== | ==Kaldi/HTK merge== | ||
| − | :* HTK2Kaldi: | + | :* HTK2Kaldi: hold. |
| − | :* Kaldi2HTK: done with implementation. | + | :* Kaldi2HTK: done with implementation. Performance improved. |
==Embedded progress== | ==Embedded progress== | ||
| − | :* | + | :* PocketSphinx migration done. Very slow. |
| − | + | :* QA LM training, done. | |
| − | :* QA LM training, | + | |
2013年4月26日 (五) 05:47的版本
目录
Data sharing
- AM/lexicon/LM are shared.
- LM count files are still in transfering.
DNN progress
400 hour DNN training
| Test Set | Tencent Baseline | bMMI | fMMI | BN | Hybrid |
|---|---|---|---|---|---|
| 1900 | 8.4 | 7.65 | 7.35 | 6.57 | |
| 2044 | 22.4 | 24.44 | 24.03 | 21.77 | |
| online1 | 35.6 | 34.66 | 34.33 | 31.44 | |
| online2 | 29.6 | 27.23 | 26.80 | 24.10 | |
| map | 24.5 | 27.54 | 27.69 | 23.79 | |
| notepad | 16 | 19.81 | 21.75 | 15.81 | |
| general | 36 | 38.52 | 38.90 | 33.61 | |
| speedup | 26.8 | 27.88 | 26.81 | 22.82 |
- Tencent baseline is with 700h online data+ 700h 863 data, HLDA+MPE, 88k lexicon
- Our results are with 400 hour AM, 88k LM. ML+bMMI
Tencent test result
- AM: 70h training data(2 day, 15 machines, 10 threads)
- LM: 88k LM
- Test case: general
| Feature | GMM-bMMI | DNN | DNN-MMI | PLP(-5,+5) | 38.4 | 26.5 | 23.8 |
|---|---|---|---|---|---|---|---|
| PLP+LDA+MLLT(-5,+5) | 38.4 | 28.7 |
GPU & CPU merge
- Invesigate the possibility to merge GPU and CPU code. GPU computing code merged to CPU.
L-1 sparse initial training
- Start to investigating.
Kaldi/HTK merge
- HTK2Kaldi: hold.
- Kaldi2HTK: done with implementation. Performance improved.
Embedded progress
- PocketSphinx migration done. Very slow.
- QA LM training, done.
