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

..

test_bpe_graph_compiler.py

Use new APIs with k2.RaggedTensor (#38)

2021-09-08 14:55:30 +08:00

test_checkpoint.py

Fix code style and add copyright. (#18)

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

test_decode.py

Refactor decode.py to make it more readable and more modular. (#44)

2021-09-20 15:44:54 +08:00

test_graph_compiler.py

Fix code style and add copyright. (#18)

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

test_lexicon.py

Fix code style and add copyright. (#18)

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

test_utils.py

Use new APIs with k2.RaggedTensor (#38)

2021-09-08 14:55:30 +08:00