summaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAge
* writing the schedulertxh182015-11-06
|
* added cross-border flushtxh182015-11-06
|
* first small tnn test seems to worktxh182015-11-06
|
* working on TNN:net_propagatetxh182015-11-03
|
* still working on TNNtxh182015-11-03
|
* ...txh182015-11-02
|
* ...txh182015-11-02
|
* still working on the tdag layertxh182015-11-01
|
* start implementing tdag_layertxh182015-10-30
|
* finished a simple version of lmseqreadertxh182015-10-30
|
* still working in lmseqreadertxh182015-10-30
|
* doingtxh182015-10-28
|
* TODO:implement lmseqreadertxh182015-10-28
|
* changed copy_rows_fromd_by_idx a bit to make it clearertxh182015-10-28
|
* added update_select_rows to doctxh182015-10-28
|
* added update_select_rows for select_linear:update speed-uptxh182015-10-27
|
* using copy_rows_fromd for select-liner:propagate, TODO:speed up ↵txh182015-10-26
| | | | select-linear:update
* discovered a copy_rows_fromd_by_idx that can be usedtxh182015-10-26
|
* simple doc changetxh182015-10-25
|\
| * changed doc pointer in the main markdowntxh182015-10-25
| |
* | added timer for profilingtxh182015-10-25
| |
* | lmptb can be run after merge from mastertxh182015-10-23
| |
* | Just come back, let's merge the new mastertxh182015-10-23
|\| | | | | | | Merge branch 'master' into txh18/rnnlm
| * Merge pull request #6 from yimmon/masterTed Yin2015-10-12
| |\ | | | | | | support batch_resize (sequence training related layers are in kaldi_seq)
| | * move sequence related layers to kaldi_seqYimmon Zhuang2015-10-10
| | |
| | * disable batch when sequence trainingYimmon Zhuang2015-10-10
| | |
| | * MMI supportYimmon Zhuang2015-10-08
| | |
| | * kaldi mpe training supportYimmon Zhuang2015-09-18
| | |
| | * Merge remote-tracking branch 'upstream/master'Yimmon Zhuang2015-09-14
| | |\
| | * \ Merge remote-tracking branch 'upstream/master'Yimmon Zhuang2015-08-27
| | |\ \
| | * \ \ .Yimmon Zhuang2015-08-27
| | |\ \ \
| | * | | | .Yimmon Zhuang2015-08-27
| | | | | |
| * | | | | enable user to set direct_update in gconf; use direct_update in the exampleDeterminant2015-10-09
| | |_|_|/ | |/| | |
| * | | | ...Determinant2015-08-31
| | | | |
| * | | | ...Determinant2015-08-30
| | | | |
| * | | | support gpu bufferingDeterminant2015-08-28
| | |_|/ | |/| |
| * | | update embedding example to use new global_transf()Determinant2015-08-27
| | |/ | |/|
| * | ...Determinant2015-08-26
| | |
| * | move global_transf to asr_trainer.luaDeterminant2015-08-26
| | |
| * | add optional parameters to mat:createDeterminant2015-08-25
| | |
| * | use more general implementation for mat:createDeterminant2015-08-25
| | |
| * | use default cuda library pathDeterminant2015-08-14
| | |
| * | add profiling for copy_rows_fromh_by_idxDeterminant2015-08-14
| |/
| * ...Determinant2015-08-06
| |
| * make network configuration example file clearerDeterminant2015-08-06
| |
| * ...Determinant2015-08-06
| |
| * do not use submodule for nerv-speechDeterminant2015-08-06
| |
| * fix typoes in nerv.errorDeterminant2015-08-06
| |
| * use expanded features and do global transf in embedding_exampleDeterminant2015-08-05
| |
| * ...Determinant2015-08-05
| |