“Wsj data”版本间的差异
来自cslt Wiki
（→RNNLM Rescore） |
|||
| 第33行： | 第33行： | ||
** decode: /nfs/disk/work/users/zhangzy/work/train_wsj_eng_new/exp/tri4b_dnn_org/decode_eval92_tri4b_dnn_org | ** decode: /nfs/disk/work/users/zhangzy/work/train_wsj_eng_new/exp/tri4b_dnn_org/decode_eval92_tri4b_dnn_org | ||
*Result | *Result | ||
| − | ** lm: | + | ** lm:3.85%,rnnlm:3.35% |
2014年10月22日 (三) 09:25的版本
- Data
- size:200M,npdata
- location:/nfs/disk/perm/data/corpora/wsj/data/wsj0/doc/lng_modl/lm_train/np_data
- dic:/work/lr/word2vector/RNN/RNN/Kaldi+RNN/RNNTEST/kaldi-trunk/egs/wsj/s5/data/local/dict_larger/wordlist.cmu
- 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:3.85%,rnnlm:3.35%
