PingFeng Luo
3f8ba23a60
Merge branch 'master' into wenetspeech
2022-01-01 20:58:17 +08:00
PingFeng Luo
c7b5e6088e
add wenetspeech recipe
2022-01-01 20:43:34 +08:00
PingFeng Luo
82329f08ff
fix style
2022-01-01 15:56:07 +08:00
PingFeng Luo
3890ff6ee8
typo
2022-01-01 15:15:22 +08:00
PingFeng Luo
54fb0d52ff
Merge branch 'master' into wenetspeech
2022-01-01 10:51:38 +08:00
PingFeng Luo
e3bce65a90
fix colab link
2022-01-01 10:50:34 +08:00
PingFeng Luo
dbac1fb27f
typo
2021-12-31 19:30:31 +08:00
PingFeng Luo
178b19f166
fix flake8 conflict
2021-12-31 19:27:00 +08:00
PingFeng Luo
bcc117879a
fix flake8 conflict
2021-12-31 19:24:35 +08:00
PingFeng Luo
54155cc164
fix style
2021-12-31 19:19:42 +08:00
PingFeng Luo
4e92553066
fix sytle
2021-12-31 19:14:53 +08:00
PingFeng Luo
6813b754e9
fix style
2021-12-31 19:11:24 +08:00
PingFeng Luo
46eab8b727
fix sytle
2021-12-31 18:57:06 +08:00
PingFeng Luo
28d1e8660e
fix sytle
2021-12-31 18:50:12 +08:00
PingFeng Luo
503275e649
Merge branch 'master' into wenetspeech
2021-12-31 18:28:22 +08:00
PingFeng Luo
f68dc1893f
add transducer-stateless-aishell recipe to readme
2021-12-31 18:24:26 +08:00
PingFeng Luo
a94f7b440e
typo
2021-12-31 11:41:39 +08:00
PingFeng Luo
4166f5706e
add transducer_stateless with char unit to AIShell
2021-12-31 10:04:36 +08:00
PingFeng Luo
1717b26cab
fix style
2021-12-31 09:40:42 +08:00
PingFeng Luo
a82d826987
fix style
2021-12-30 18:57:56 +08:00
PingFeng Luo
8b8cf6c68e
fix style
2021-12-30 18:43:47 +08:00
PingFeng Luo
f49de8e8e0
Merge branch 'master' of github.com:pingfengluo/icefall
2021-12-30 12:08:30 +08:00
PingFeng Luo
18cdea4745
add transducer_stateless with char unit to AIShell
2021-12-30 11:43:26 +08:00
Fangjun Kuang
413b2e8569
Add git sha1 to RESULTS.md for conformer encoder + stateless decoder. ( #160 )
2021-12-28 12:04:01 +08:00
PingFeng Luo
234307f33a
Merge branch 'master' of https://github.com/k2-fsa/icefall
2021-12-27 16:43:39 +08:00
Fangjun Kuang
14c93add50
Remove batchnorm, weight decay, and SOS from transducer conformer encoder ( #155 )
...
* Remove batchnorm, weight decay, and SOS.
* Make --context-size configurable.
* Update results.
2021-12-27 16:01:10 +08:00
Fangjun Kuang
8187d6236c
Minor fix to maximum number of symbols per frame for RNN-T decoding. ( #157 )
...
* Minor fix to maximum number of symbols per frame RNN-T decoding.
* Minor fixes.
2021-12-24 21:48:40 +08:00
PingFeng Luo
c7df25bd5b
add transducer_stateless to AIShell
2021-12-23 14:59:35 +08:00
Fangjun Kuang
5b6699a835
Minor fixes to the RNN-T Conformer model ( #152 )
...
* Disable weight decay.
* Remove input feature batchnorm..
* Replace BatchNorm in the Conformer model with LayerNorm.
* Use tanh in the joint network.
* Remove sos ID.
* Reduce the number of decoder layers from 4 to 2.
* Minor fixes.
* Fix typos.
2021-12-23 13:54:25 +08:00
PingFeng Luo
1b45d37080
Merge branch 'master' of https://github.com/k2-fsa/icefall
2021-12-23 11:24:33 +08:00
Fangjun Kuang
fb6a57e9e0
Increase the size of the context in the RNN-T decoder. ( #153 )
2021-12-23 07:55:02 +08:00
Fangjun Kuang
cb04c8a750
Limit the number of symbols per frame in RNN-T decoding. ( #151 )
2021-12-18 11:00:42 +08:00
Fangjun Kuang
1d44da845b
RNN-T Conformer training for LibriSpeech ( #143 )
...
* Begin to add RNN-T training for librispeech.
* Copy files from conformer_ctc.
Will edit it.
* Use conformer/transformer model as encoder.
* Begin to add training script.
* Add training code.
* Remove long utterances to avoid OOM when a large max_duraiton is used.
* Begin to add decoding script.
* Add decoding script.
* Minor fixes.
* Add beam search.
* Use LSTM layers for the encoder.
Need more tunings.
* Use stateless decoder.
* Minor fixes to make it ready for merge.
* Fix README.
* Update RESULT.md to include RNN-T Conformer.
* Minor fixes.
* Fix tests.
* Minor fixes.
* Minor fixes.
* Fix tests.
2021-12-18 07:42:51 +08:00
Wei Kang
76a51bf037
Fix aishell tdnn_lstm_ctc decoding ( #149 )
2021-12-14 14:42:58 +08:00
Wei Kang
a183d5bfd7
Remove batchnorm ( #147 )
...
* Remove batch normalization
* Minor fixes
* Fix typo
* Fix comments
* Add assertion for use_feat_batchnorm
2021-12-14 08:20:03 +08:00
Fangjun Kuang
95af039733
RNN-T training for yesno. ( #141 )
...
* RNN-T training for yesno.
* Rename Jointer to Joiner.
2021-12-07 21:44:37 +08:00
Fangjun Kuang
1aff64b708
Apply layer normalization to the output of each gate in LSTM/GRU. ( #139 )
...
* Apply layer normalization to the output of each gate in LSTM.
* Apply layer normalization to the output of each gate in GRU.
* Add projection support to LayerNormLSTMCell.
* Add GPU tests.
* Use typeguard.check_argument_types() to validate type annotations.
* Add typeguard as a requirement.
* Minor fixes.
* Fix CI.
* Fix CI.
* Fix test failures for torch 1.8.0
* Fix errors.
2021-12-07 18:38:03 +08:00
pingfengluo
d1adc25338
Update AIShell recipe result ( #140 )
...
* add MMI to AIShell
* fix MMI decode graph
* export model
* typo
* fix code style
* typo
* fix data prepare to just use train text by uid
* use a faster way to get the intersection of train and aishell_transcript_v0.8.txt
* update AIShell result
* update
* typo
2021-12-04 14:43:04 +08:00
PingFeng Luo
cdc15634ec
typo
2021-12-04 11:49:33 +08:00
PingFeng Luo
45d31e5f34
update
2021-12-04 11:40:14 +08:00
PingFeng Luo
3351106e3b
fix conflicts
2021-12-04 11:30:36 +08:00
PingFeng Luo
0af744e518
update AIShell result
2021-12-04 11:11:49 +08:00
PingFeng Luo
d7f9dacf0d
use a faster way to get the intersection of train and aishell_transcript_v0.8.txt
2021-12-03 14:33:10 +08:00
PingFeng Luo
00b5ac5815
fix data prepare to just use train text by uid
2021-12-03 11:55:28 +08:00
pingfengluo
89b84208aa
add phone based LF-MMI training to AIShell recipe ( #137 )
...
* add MMI to AIShell
* fix MMI decode graph
* export model
* typo
* fix code style
* typo
2021-12-02 12:32:23 +08:00
PingFeng Luo
bc0b6eed5c
typo
2021-12-02 12:13:05 +08:00
PingFeng Luo
e14decf75e
fix code style
2021-12-02 11:11:50 +08:00
PingFeng Luo
08db15d8d5
typo
2021-12-02 10:19:36 +08:00
PingFeng Luo
85db336efb
Merge branch 'master' of https://github.com/k2-fsa/icefall
2021-12-02 10:10:19 +08:00
PingFeng Luo
cf50e16047
export model
2021-12-02 10:06:42 +08:00