Fangjun Kuang 12d647d899

Add a note about the CUDA OOM error. (#94) ...

* Add a note about the CUDA OOM error.

Some users consider this kind of OOM as an error during decoding,
but actually it is not. This pull request clarifies that.

* Fix style issues.

2021-10-29 12:17:56 +08:00

..

dataset

Add recipe for the yes_no dataset. (#16)

2021-08-23 11:36:29 +08:00

shared

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

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

__init__.py

Minor fixes after review.

2021-07-20 10:02:20 +08:00

ali.py

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

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

bpe_graph_compiler.py

Fix code style and add copyright. (#18)

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

checkpoint.py

Use GPU for averaging checkpoints if possible. (#84)

2021-10-26 17:10:04 +08:00

decode.py

Add a note about the CUDA OOM error. (#94)

2021-10-29 12:17:56 +08:00

dist.py

Fix code style and add copyright. (#18)

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

graph_compiler.py

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

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

lexicon.py

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

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

mmi_graph_compiler.py

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

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

mmi.py

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

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

utils.py

Extract framewise alignment information using CTC decoding (#39)

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