“RNN test”版本间的差异
来自cslt Wiki
（→RNNLM Rescore） |
（→RNNLM Rescore） |
||
| 第32行： | 第32行： | ||
*test set | *test set | ||
** location: /nfs/disk/work/users/zhangzy/work/train_wsj_eng_new/dt/test_eval92 | ** location: /nfs/disk/work/users/zhangzy/work/train_wsj_eng_new/dt/test_eval92 | ||
| + | ** decode: /nfs/disk/work/users/zhangzy/work/train_wsj_eng_new/exp/tri4b_dnn_org/decode_eval92_tri4b_dnn_org | ||
*Result | *Result | ||
2014年9月17日 (三) 03:20的版本
wsj Test
wsj_data
- Data
- size:200M,npdata
- parameter
rand_seed=1
nwords=10000 # This is how many words we're putting in the vocab of the RNNLM.
hidden=320
class=300 # Num-classes... should be somewhat larger than sqrt of nwords.
direct=2000 # Number of weights that are used for "direct" connections, in millions.
rnnlm_ver=rnnlm-0.3e # version of RNNLM to use
threads=1 # for RNNLM-HS
bptt=2 # length of BPTT unfolding in RNNLM
bptt_block=20 # length of BPTT unfolding in RNNLM
- Train RNNLM set
| Parameters | hidden | class | direct | bbt | bptt_block | threads | direct-order | rand_seed | nwords | time(min) |
|---|---|---|---|---|---|---|---|---|---|---|
| set1 | 320 | 300 | 2000 | 2 | 20 | 1 | 4 | 1 | 10000 | 3380(56h) |
RNNLM Rescore
- Acoustic Model
- location: /nfs/disk/work/users/zhangzy/work/train_wsj_eng_new/exp/tri4b_dnn_org/decode_eval92_tri4b_dnn_org
- test set
- location: /nfs/disk/work/users/zhangzy/work/train_wsj_eng_new/dt/test_eval92
- decode: /nfs/disk/work/users/zhangzy/work/train_wsj_eng_new/exp/tri4b_dnn_org/decode_eval92_tri4b_dnn_org
- Result
