| Commit message (Collapse) | Author | Age |
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
|\ |
|
| | |
|
|\ \
| | |
| | |
| | | |
Merge branch 'master' into txh18/rnnlm
|
| |/ |
|
| | |
|
| | |
|
| | |
|
|/ |
|
|
|
|
| |
unreproducable, I changed select_linear layer update back to line-by-line
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
|\
| |
| | |
support batch_resize (sequence training related layers are in kaldi_seq)
|
| | |
|
| | |
|
| | |
|
|/ |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
|
|