Mingshuang Luo
bc101093c6
Delete train.py
2021-09-29 17:36:30 +08:00
Mingshuang Luo
00b2d4c9c7
Rename train_lossrecord_tdnn.py to train.py
2021-09-29 17:35:58 +08:00
Mingshuang Luo
84eb064675
Add files via upload
2021-09-29 17:35:24 +08:00
Mingshuang Luo
f03fb67aa1
Delete train.py
2021-09-29 17:35:03 +08:00
Mingshuang Luo
426418c703
Rename train_lossrecord_con.py to train.py
2021-09-29 17:34:34 +08:00
Mingshuang Luo
787ca3b89c
Add files via upload
2021-09-29 17:33:56 +08:00
Mingshuang Luo
6de7f0c062
Delete train.py
2021-09-29 17:33:32 +08:00
Mingshuang Luo
7c1819dddd
Add files via upload
2021-09-29 17:33:03 +08:00
Mingshuang Luo
94ef8208b1
Delete utils.py
2021-09-29 17:32:34 +08:00
Mingshuang Luo
de9b2a9cd1
Update train.py
2021-09-29 16:54:21 +08:00
Mingshuang Luo
a0994ee58a
Update utils.py
2021-09-29 16:48:00 +08:00
Mingshuang Luo
7faab70ddf
Update utils.py
2021-09-29 16:43:01 +08:00
Mingshuang Luo
ec3b1bb015
Update utils.py
2021-09-29 16:11:23 +08:00
Mingshuang Luo
d0986e9787
Update utils.py
2021-09-29 16:04:56 +08:00
Mingshuang Luo
d04271219c
Update utils.py
2021-09-29 16:01:53 +08:00
Mingshuang Luo
28fa30a255
Update utils.py
2021-09-29 14:13:31 +08:00
Mingshuang Luo
8d07ce2185
Update utils.py
2021-09-29 13:11:52 +08:00
Mingshuang Luo
1c0792796b
Update train.py
2021-09-29 12:57:23 +08:00
Mingshuang Luo
43cf016ae5
Update train.py
2021-09-29 12:56:47 +08:00
Mingshuang Luo
34e36a926b
Update train.py
2021-09-29 12:55:42 +08:00
Mingshuang Luo
597ff01158
Update train.py
2021-09-29 12:51:38 +08:00
Mingshuang Luo
0fa46bf68a
Update train.py
2021-09-29 12:49:59 +08:00
Mingshuang Luo
e74e75acc6
Use LossRecord to record and print loss for the training process
2021-09-29 10:08:38 +08:00
Mingshuang Luo
73f21a379b
Merge branch 'k2-fsa:master' into master
2021-09-27 15:34:08 +08:00
Fangjun Kuang
707d7017a7
Support pure ctc decoding requiring neither a lexicon nor an n-gram LM ( #58 )
...
* Rename lattice_score_scale to nbest_scale.
* Support pure CTC decoding requiring neither a lexicion nor an n-gram LM.
* Fix style issues.
* Fix a typo.
* Minor fixes.
2021-09-26 14:21:49 +08:00
Mingshuang Luo
6c4a58273f
Fix some spelling errors.
2021-09-26 12:55:51 +08:00
Mingshuang Luo
6abd1bcd0a
Fix some spelling errors.
2021-09-26 12:54:35 +08:00
Mingshuang Luo
662690aa8b
Merge branch 'k2-fsa:master' into master
2021-09-26 12:51:30 +08:00
Fangjun Kuang
455693aede
Fix hasattr of AttributeDict. ( #52 )
2021-09-22 16:37:20 +08:00
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
Fangjun Kuang
cc77cb3459
Fix decode.py to remove the correct axis. ( #50 )
...
* Fix decode.py to remove the correct axis.
* Run GitHub actions manually.
2021-09-17 16:49:03 +08:00
Wei Kang
9a6e0489c8
update api for RaggedTensor ( #45 )
...
* Fix code style
* update k2 version in CI
* fix compile hlg
2021-09-14 16:39:56 +08:00
Fangjun Kuang
a2be2896a9
Fix the link to k2's installation doc. ( #46 )
2021-09-14 13:39:52 +08:00
Wei Kang
24656e9749
Update docs and remove unnecessary arguments ( #42 )
...
* Fix typo in docs
* Update docs and remove unnecessary arguments
* Fix code style
2021-09-13 18:28:57 +08:00
Fangjun Kuang
f792b466bf
Change default value of lattice-score-scale from 1.0 to 0.5 ( #41 )
...
* Change the default value of lattice-score-scale from 1.0 to 0.5
* Fix CI.
2021-09-13 10:49:18 +08:00
Fangjun Kuang
7f8e3a673a
Add commands for reproducing. ( #40 )
...
* Add commands for reproducing.
* Use --bucketing-sampler by default.
2021-09-09 13:50:31 +08:00
Fangjun Kuang
abadc71415
Use new APIs with k2.RaggedTensor ( #38 )
...
* Use new APIs with k2.RaggedTensor
* Fix style issues.
* Update the installation doc, saying it requires at least k2 v1.7
* Use k2 v1.7
2021-09-08 14:55:30 +08:00
Fangjun Kuang
331e5eb7ab
[doc] Fix typos. ( #31 )
2021-09-02 07:12:37 +08:00
Mingshuang Luo
5baa6a9f1c
fix a spelling mistake (tourch->touch) ( #29 )
2021-08-25 21:41:46 +08:00
Mingshuang Luo
eed3fc5610
Correct some spelling mistakes ( #28 )
...
* Update index.rst (AS->ASR)
* Update conformer_ctc.rst (pretraind->pretrained)
2021-08-25 17:48:34 +08:00
Mingshuang Luo
63de376e94
Update conformer_ctc.rst (pretraind->pretrained)
2021-08-25 17:40:48 +08:00
Mingshuang Luo
8a478c5610
Update index.rst (AS->ASR)
2021-08-25 17:34:30 +08:00
Fangjun Kuang
184dbb3ea5
Add documentation about code style and creating new recipes. ( #27 )
2021-08-25 14:48:41 +08:00
Fangjun Kuang
96e7f5c7ea
Release v0.1 ( #26 )
2021-08-24 21:30:30 +08:00
pkufool
f4223ee110
Add TDNN-LSTM-CTC Results ( #25 )
...
* Add tdnn-lstm pretrained model and results
* Add docs for TDNN-LSTM-CTC
* Minor fix
* Fix typo
* Fix style checking
2021-08-24 21:09:27 +08:00
Fangjun Kuang
1bd5dcc8ac
WIP: Add doc for the LibriSpeech recipe. ( #24 )
...
* WIP: Add doc for the LibriSpeech recipe.
* Add more doc for LibriSpeech recipe.
* Add more doc for the LibriSpeech recipe.
* More doc.
2021-08-24 20:28:32 +08:00
Fangjun Kuang
01da00dca0
WIP: Add documentation. ( #22 )
...
* Begin to add documentation.
* WIP: Add documentation.
* Fix a typo.
* Add more doc for the recipe yesno.
* Add more doc for the yesno recipe.
2021-08-24 14:28:08 +08:00
Fangjun Kuang
57cb611665
[yesno] Remove padding in TDNN ( #21 )
...
* Disable SpecAug for yesno.
Also replace Adam with SGD.
* Remove padding in the model to make the results reproducible.
2021-08-23 15:59:36 +08:00
Fangjun Kuang
6c2c9b9d74
Add recipe for the yes_no dataset. ( #16 )
...
* Add recipe for the yes_no dataset.
* Refactoring: Remove unused code.
* Add Colab notebook for the yesno dataset.
* Add GitHub actions to run yesno.
* Fix a typo.
* Minor fixes.
* Train more epochs for GitHub actions.
* Minor fixes.
* Minor fixes.
* Fix style issues.
2021-08-23 11:36:29 +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
