mirrors/icefall
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
1,458 Commits 5 Branches 3 Tags
Commit Graph

21 Commits

Author SHA1 Message Date
Daniel Povey
28e5f46854 Update checkpoint.py to deal with int params 2022-10-07 17:06:38 +08:00
Daniel Povey
ca09b9798f Remove decomposition code from checkpoint.py; restore double precision model_avg 2022-06-01 14:01:58 +08:00
Daniel Povey
da2ffd4d27 Do average computation in double precision 2022-05-31 14:39:21 +08:00
Daniel Povey
b2259184b5 Use single precision for model average; increase average-period to 200. 2022-05-31 14:31:46 +08:00
Daniel Povey
8d4c987e21 Update checkpoint.py to support decompose argument 2022-05-31 14:25:45 +08:00
Daniel Povey
8e454bcf9e Exclude size=500 dim from projection; try to use double for model average 2022-05-26 15:15:27 +08:00
Zengwei Yao
20f092e709
Support decoding with averaged model when using --iter (#353) 
* support decoding with averaged model when using --iter

* minor fix

* monir fix of copyright date
 2022-05-07 13:09:11 +08:00
Zengwei Yao
c059ef3169
Keep model_avg on cpu (#348) 
* keep model_avg on cpu

* explicitly convert model_avg to cpu

* minor fix

* remove device convertion for model_avg

* modify usage of the model device in train.py

* change model.device to next(model.parameters()).device for decoding

* assert params.start_epoch>0

* assert params.start_epoch>0, params.start_epoch
 2022-05-07 10:42:34 +08:00
Zengwei Yao
00c48ec1f3
Model average (#344) 
* First upload of model average codes.

* minor fix

* update decode file

* update .flake8

* rename pruned_transducer_stateless3 to pruned_transducer_stateless4

* change epoch number counter starting from 1 instead of 0

* minor fix of pruned_transducer_stateless4/train.py

* refactor the checkpoint.py

* minor fix, update docs, and modify the epoch number to count from 1 in the pruned_transducer_stateless4/decode.py

* update author info

* add docs of the scaling in function average_checkpoints_with_averaged_model
 2022-05-05 21:20:04 +08:00
Fangjun Kuang
9aeea3e1af
Support averaging models with weight tying. (#333) 2022-04-26 13:32:03 +08:00
Mingshuang Luo
93c60a9d30
Code style check for librispeech pruned transducer stateless2 (#308) 2022-04-11 22:15:18 +08:00
Daniel Povey
6eb6d9b4cd
Merge pull request #288 from danpovey/reworked_model 
Reworked model
 2022-04-11 15:03:08 +08:00
Daniel Povey
d1e4ae788d Refactor how learning rate is set. 2022-04-10 15:25:27 +08:00
Fangjun Kuang
87cf9231ea
Support specifying iteration number of checkpoints for decoding. (#289) 2022-04-03 13:02:08 +08:00
Fangjun Kuang
ae564f91e6
Periodically saving checkpoint after processing given number of batches (#259) 
* Periodically saving checkpoint after processing given number of batches.
 2022-03-20 23:51:33 +08:00
Fangjun Kuang
ec591698b0
Associate a cut with token alignment (without repeats) (#125) 
* WIP: Associate a cut with token alignment (without repeats)

* Save framewise alignments with/without repeats.

* Minor fixes.
 2021-11-29 18:50:54 +08:00
Fangjun Kuang
8cb7f712e4
Use GPU for averaging checkpoints if possible. (#84) 2021-10-26 17:10:04 +08:00
pkufool
19c4214958
Fix code style and add copyright. (#18) 
* Fix style and add copyright

* Minor fix

* Remove duplicate lines

* Reformat conformer.py by black

* Reformat code style with black.

* Fix github workflows

* Fix lhotse installation

* Install icefall requirements

* Update k2 version, remove lhotse from test workflow
 2021-08-23 10:43:59 +08:00
Fangjun Kuang
8469f9ae0a
Refactor asr_datamodule. (#15) 
* WIP: Refactor asr_datamodule.

* Fixes after review.

* Minor fixes.
 2021-08-21 09:53:46 +08:00
Fangjun Kuang
d3101fb005 Fix loading checkpoint in DDP training. 2021-07-26 08:08:14 +08:00
Fangjun Kuang
f3542c7793 Add CTC training. 2021-07-24 17:13:20 +08:00