mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-08 17:42:21 +00:00
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/librispeech/ASR
History
Fangjun Kuang 21096e99d8
Update result for the librispeech recipe using vocab size 500 and att rate 0.8 (#113) 
* Update RESULTS using vocab size 500, att rate 0.8

* Update README.

* Refactoring.

Since FSAs in an Nbest object are linear in structure, we can
add the scores of a path to compute the total scores.

* Update documentation.

* Change default vocab size from 5000 to 500.
2021-11-10 14:32:52 +08:00
..
conformer_ctc
Update result for the librispeech recipe using vocab size 500 and att rate 0.8 (#113)
2021-11-10 14:32:52 +08:00
conformer_mmi
Use pre-sorted text to generate token ids for attention decoder. (#98)
2021-10-29 13:46:41 +08:00
local
Add MMI training with word pieces as modelling unit. (#6)
2021-10-18 15:20:32 +08:00
tdnn_lstm_ctc
Use GPU for averaging checkpoints if possible. (#84)
2021-10-26 17:10:04 +08:00
prepare.sh
Add MMI training with word pieces as modelling unit. (#6)
2021-10-18 15:20:32 +08:00
README.md
Release v0.1 (#26)
2021-08-24 21:30:30 +08:00
RESULTS.md
Update result for the librispeech recipe using vocab size 500 and att rate 0.8 (#113)
2021-11-10 14:32:52 +08:00
shared
Refactoring (#4)
2021-08-04 14:53:02 +08:00

README.md

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