“Wsj data”版本间的差异
来自cslt Wiki
（以“*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 cl...”为内容创建页面） |
|||
| 第1行： | 第1行： | ||
*Data | *Data | ||
:* size:200M,npdata | :* size:200M,npdata | ||
| + | :* location:/nfs/disk/perm/data/corpora/wsj/data/wsj0/doc/lng_modl/lm_train/np_data | ||
*parameter | *parameter | ||
rand_seed=1 | rand_seed=1 | ||
2014年10月10日 (五) 03:29的版本
- Data
- size:200M,npdata
- location:/nfs/disk/perm/data/corpora/wsj/data/wsj0/doc/lng_modl/lm_train/np_data
- 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/data/train_si284
- 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
- lm:4.16%,rnnlm:3.47%
