PingFeng Luo
f68dc1893f
add transducer-stateless-aishell recipe to readme
2021-12-31 18:24:26 +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
PingFeng Luo
4b6edaa4a3
fix MMI decode graph
2021-12-01 16:37:12 +08:00
PingFeng Luo
a54f9a9b41
add MMI to AIShell
2021-11-30 16:52:21 +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
243fb9723c
Fix an error introduced while supporting torchscript. ( #134 )
...
Should be `G.dummy = 1`, not `G["dummy"] = 1`.
2021-11-27 09:07:04 +08:00
Fangjun Kuang
0e541f5b5d
Print hostname and IP address to the log. ( #131 )
...
We are using multiple machines to do various experiments. It makes
life easier to know which experiment is running on which machine
if we also log the IP and hostname of the machine.
2021-11-26 11:25:59 +08:00
LIyong.Guo
00e2f0ade8
Draft streaming decoding ( #89 )
...
* reusable parts from conformer_ctc
* streaming conformer code
* a trained model
2021-11-24 19:35:18 +08:00
Lucky Wong
769a9791ec
Fix no attribute 'data' error. ( #129 )
2021-11-22 18:31:04 +08:00
Wei Kang
e2c9c728d9
Update aishell tensorboard log for new LabelSmoothing loss ( #128 )
...
* Update aishell tensorboard log for new LabelSmoothing loss
* Minor fixes
2021-11-22 12:26:44 +08:00
Wei Kang
4151cca147
Add torch script support for Aishell and update documents ( #124 )
...
* Add aishell recipe
* Remove unnecessary code and update docs
* adapt to k2 v1.7, add docs and results
* Update conformer ctc model
* Update docs, pretrained.py & results
* Fix code style
* Fix code style
* Fix code style
* Minor fix
* Minor fix
* Fix pretrained.py
* Update pretrained model & corresponding docs
* Export torch script model for Aishell
* Add C++ deployment docs
* Minor fixes
* Fix unit test
* Update Readme
2021-11-19 16:37:05 +08:00
Wei Kang
30c43b7f69
Add aishell recipe ( #30 )
...
* Add aishell recipe
* Remove unnecessary code and update docs
* adapt to k2 v1.7, add docs and results
* Update conformer ctc model
* Update docs, pretrained.py & results
* Fix code style
* Fix code style
* Fix code style
* Minor fix
* Minor fix
* Fix pretrained.py
* Update pretrained model & corresponding docs
2021-11-18 10:00:47 +08:00
Fangjun Kuang
0660d12e4e
Fix computing WERs for empty hypotheses ( #118 )
...
* Fix computing WERs when empty lattices are generated.
* Minor fixes.
2021-11-17 19:25:47 +08:00
Fangjun Kuang
336283f872
New label smoothing ( #109 )
...
* Modify label smoothing to match the one implemented in PyTorch.
* Enable CI for torch 1.10
* Fix CI errors.
* Fix CI installation errors.
* Fix CI installation errors.
* Minor fixes.
* Minor fixes.
* Minor fixes.
* Minor fixes.
* Minor fixes.
* Fix CI errors.
2021-11-17 19:24:07 +08:00
Mingshuang Luo
10e46f3e1d
A little changes for timit recipe ( #122 )
...
* Update train.py
* Update train.py
* Update train.py
* Update tdnn_ligru_ctc.rst
2021-11-17 16:13:51 +08:00
Mingshuang Luo
2e0f255ada
Add timit recipe (including the code scripts and the docs) for icefall ( #114 )
...
* add timit recipe for icefall
* add shared file
* update the docs for timit recipe
* Delete shared
* update the timit recipe and check style
* Update model.py
* Do some changes
* Update model.py
* Update model.py
* Add README.md and RESULTS.md
* Update RESULTS.md
* Update README.md
* update the docs for timit recipe
2021-11-17 11:23:45 +08:00
Fangjun Kuang
68506609ad
Set fsa.properties to None after changing its labels in-place. ( #121 )
2021-11-16 23:11:30 +08:00
Daniel Povey
b9452235d5
Merge pull request #117 from csukuangfj/fix-empty-lattice
...
Handle empty lattices in attention decoder rescoring.
2021-11-11 16:26:02 +08:00
Fangjun Kuang
5b10310bd1
Handle empty lattices in attention decoder rescoring.
2021-11-11 15:42:30 +08:00