“Wsj data”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
Lr讨论 | 贡献
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:4.16%,rnnlm:3.47%
+
** 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
Train Set Environment
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%