Fangjun Kuang 53b79fafa7

Add MMI training with word pieces as modelling unit. (#6) ...

* Fix an error in TDNN-LSTM training.

* WIP: Refactoring

* Refactor transformer.py

* Remove unused code.

* Minor fixes.

* Fix decoder padding mask.

* Add MMI training with word pieces.

* Remove unused files.

* Minor fixes.

* Refactoring.

* Minor fixes.

* Use pre-computed alignments in LF-MMI training.

* Minor fixes.

* Update decoding script.

* Add doc about how to check and use extracted alignments.

* Fix style issues.

* Fix typos.

* Fix style issues.

* Disable macOS tests for now.

2021-10-18 15:20:32 +08:00

..

test_ali.py

Add MMI training with word pieces as modelling unit. (#6)

2021-10-18 15:20:32 +08:00

test_bpe_graph_compiler.py

Add MMI training with word pieces as modelling unit. (#6)

2021-10-18 15:20:32 +08:00

test_checkpoint.py

Fix code style and add copyright. (#18)

2021-08-23 10:43:59 +08:00

test_decode.py

Support pure ctc decoding requiring neither a lexicon nor an n-gram LM (#58)

2021-09-26 14:21:49 +08:00

test_graph_compiler.py

Fix code style and add copyright. (#18)

2021-08-23 10:43:59 +08:00

test_lexicon.py

Add MMI training with word pieces as modelling unit. (#6)

2021-10-18 15:20:32 +08:00

test_mmi_graph_compiler.py

Add MMI training with word pieces as modelling unit. (#6)

2021-10-18 15:20:32 +08:00

test_utils.py

Extract framewise alignment information using CTC decoding (#39)

2021-10-18 14:24:33 +08:00