diff options
| author | Determinant <ted.sybil@gmail.com> | 2016-03-10 20:31:51 +0800 |
|---|---|---|
| committer | Determinant <ted.sybil@gmail.com> | 2016-03-10 20:31:51 +0800 |
| commit | 046d6d30b88462407c4acde3d7c47e94ef083b94 (patch) | |
| tree | bc61fc930543d56acc0efa78ab4a3192d98408af | |
| parent | 731b55496cedb46dff3486e7dd38f51b083ce113 (diff) | |
...alpha-1
| -rw-r--r-- | tutorial/howto_pretrain_from_kaldi.rst | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/tutorial/howto_pretrain_from_kaldi.rst b/tutorial/howto_pretrain_from_kaldi.rst index 6b8253a..8f6e0ad 100644 --- a/tutorial/howto_pretrain_from_kaldi.rst +++ b/tutorial/howto_pretrain_from_kaldi.rst @@ -122,8 +122,7 @@ How to Use a Pretrained nnet Model from Kaldi :: - cat your_trained_params.nerv your_global_trans.nerv > all.nerv - <nerv_home>/install/bin/nerv nerv_to_kaldi.lua timit_mybaseline.lua all.nerv your_kaldi_output.nnet + <nerv_home>/install/bin/nerv nerv_to_kaldi.lua timit_mybaseline.lua your_trained_params.nerv your_kaldi_output.nnet - Finally, locate the directory of stage 2: ``<timit_home>/exp/dnn4_pretrain-dbn_dnn`` and temporarily change the |