Fangjun Kuang
1ce4349c17
Merge adb54aea91abe211b19ec75eeb422b15a3867405 into 6a091da0b0543befb0492848d3583700c274d111
2022-03-23 12:52:43 +08:00
Fangjun Kuang
50d2281524
Add modified transducer loss for AIShell dataset ( #219 )
...
* Add modified transducer for aishell.
* Minor fixes.
* Add extra data in transducer training.
The extra data is from http://www.openslr.org/62/
* Update export.py and pretrained.py
* Update CI to install pretrained models with aishell.
* Update results.
* Update results.
* Update README.
* Use symlinks to avoid copies.
2022-03-02 16:02:38 +08:00
Fangjun Kuang
adb54aea91
Add backoff arcs to the start state to handle OOV word.
2022-02-15 12:33:53 +08:00
Fangjun Kuang
5af23efa69
Keep disambig tokens and backoff arcs in LG.
2022-02-10 20:28:59 +08:00
Fangjun Kuang
954b4efff3
WIP: Use shallow fusion in modified beam search.
2022-02-08 20:40:45 +08:00
Fangjun Kuang
a8150021e0
Use modified transducer loss in training. ( #179 )
...
* Use modified transducer loss in training.
* Minor fix.
* Add modified beam search.
* Add modified beam search.
* Minor fixes.
* Fix typo.
* Update RESULTS.
* Fix a typo.
* Minor fixes.
2022-02-07 18:37:36 +08:00
Fangjun Kuang
14c93add50
Remove batchnorm, weight decay, and SOS from transducer conformer encoder ( #155 )
...
* Remove batchnorm, weight decay, and SOS.
* Make --context-size configurable.
* Update results.
2021-12-27 16:01:10 +08:00
Fangjun Kuang
8187d6236c
Minor fix to maximum number of symbols per frame for RNN-T decoding. ( #157 )
...
* Minor fix to maximum number of symbols per frame RNN-T decoding.
* Minor fixes.
2021-12-24 21:48:40 +08:00
Fangjun Kuang
fb6a57e9e0
Increase the size of the context in the RNN-T decoder. ( #153 )
2021-12-23 07:55:02 +08:00
Fangjun Kuang
cb04c8a750
Limit the number of symbols per frame in RNN-T decoding. ( #151 )
2021-12-18 11:00:42 +08:00
