Mingshuang Luo
bdf02f69d6
pad 1 without 0.01 weight for exp
2022-02-07 11:07:57 +08:00
Mingshuang Luo
7df98eb000
pad 1 with torch.nn.functional.pad
2022-01-26 13:00:18 +08:00
Mingshuang Luo
cbc6f01861
modified conv1dabs attention with pad 1
2022-01-26 11:46:03 +08:00
Mingshuang Luo
ae667f4801
Will try to add a weight 0.01 before the exp operation
2022-01-14 14:31:56 +08:00
Mingshuang Luo
99274cbb8f
Operation for feedforward+mha+conv1dabs+conv+macaron.
2022-01-11 10:22:11 +08:00
Mingshuang Luo
309461c185
Do some changes for modified attention.
2022-01-10 14:36:24 +08:00
Mingshuang Luo
9142bbb17d
Update conformer.py
2021-12-13 16:02:25 +08:00
Mingshuang Luo
4392da7235
Update the modified attention codes
2021-12-13 15:15:15 +08:00
Mingshuang Luo
e442369987
Some experiments with modified attention
2021-12-13 13:21:07 +08:00
Fangjun Kuang
a80e58e15d
Refactor decode.py to make it more readable and more modular. ( #44 )
...
* Refactor decode.py to make it more readable and more modular.
* Fix an error.
Nbest.fsa should always have token IDs as labels and
word IDs as aux_labels.
* Add nbest decoding.
* Compute edit distance with k2.
* Refactor nbest-oracle.
* Add rescore with nbest lists.
* Add whole-lattice rescoring.
* Add rescoring with attention decoder.
* Refactoring.
* Fixes after refactoring.
* Fix a typo.
* Minor fixes.
* Replace [] with () for shapes.
* Use k2 v1.9
* Use Levenshtein graphs/alignment from k2 v1.9
* [doc] Require k2 >= v1.9
* Minor fixes.
2021-09-20 15:44:54 +08:00
Wei Kang
24656e9749
Update docs and remove unnecessary arguments ( #42 )
...
* Fix typo in docs
* Update docs and remove unnecessary arguments
* Fix code style
2021-09-13 18:28:57 +08:00
pkufool
19c4214958
Fix code style and add copyright. ( #18 )
...
* Fix style and add copyright
* Minor fix
* Remove duplicate lines
* Reformat conformer.py by black
* Reformat code style with black.
* Fix github workflows
* Fix lhotse installation
* Install icefall requirements
* Update k2 version, remove lhotse from test workflow
2021-08-23 10:43:59 +08:00
Fangjun Kuang
5a0b9bcb23
Refactoring ( #4 )
...
* Fix an error in TDNN-LSTM training.
* WIP: Refactoring
* Refactor transformer.py
* Remove unused code.
* Minor fixes.
2021-08-04 14:53:02 +08:00
Fangjun Kuang
4ccae509d3
WIP: Begin to add BPE decoding
2021-07-26 20:06:58 +08:00
