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
..
2021-09-14 16:39:56 +08:00
2021-08-16 19:01:25 +08:00
2021-08-24 21:30:30 +08:00
2021-09-09 13:50:31 +08:00
2021-08-04 14:53:02 +08:00

Please refer to https://icefall.readthedocs.io/en/latest/recipes/librispeech.html for how to run models in this recipe.