PF Luo
277cc3f9bf
update aishell-1 recipe with k2.rnnt_loss ( #215 )
...
* update aishell-1 recipe with k2.rnnt_loss
* fix flak8 style
* typo
* add pretrained model link to result.md
2022-02-19 15:56:39 +08:00
Duo Ma
827b9df51a
Updated Aishell-1 transducer-stateless result ( #217 )
...
* Update RESULTS.md
* Update RESULTS.md
2022-02-19 15:56:04 +08:00
Wei Kang
b702281e90
Use k2 pruned transducer loss to train conformer-transducer model ( #194 )
...
* Using k2 pruned version transducer loss to train model
* Fix style
* Minor fixes
2022-02-17 13:33:54 +08:00
Wang, Guanbo
e8eb408760
Incremental pruning threshold ( #214 )
...
* Incremental pruning threshold
* flake8
* black
* minor fix
2022-02-16 16:59:27 +08:00
Daniel Povey
2af1b3af98
Remove ReLU in attention
2022-02-14 19:39:19 +08:00
Daniel Povey
d187ad8b73
Change max_frames from 0.2 to 0.15
2022-02-11 16:24:17 +08:00
Daniel Povey
4cd2c02fff
Fix num_time_masks code; revert 0.8 to 0.9
2022-02-10 15:53:11 +08:00
Daniel Povey
c170c53006
Change p=0.9 to p=0.8 in SpecAug
2022-02-10 14:59:14 +08:00
Daniel Povey
8aa50df4f0
Change p=0.5->0.9, mask_fraction 0.3->0.2
2022-02-09 22:52:53 +08:00
Wang, Guanbo
70a3c56a18
Fix librispeech train.py ( #211 )
...
* fix librispeech train.py
* remove note
2022-02-09 16:42:28 +08:00
Daniel Povey
dd19a6a2b1
Fix to num_feature_masks bug I introduced; reduce max_frames_mask_fraction 0.4->0.3
2022-02-09 12:02:19 +08:00
Daniel Povey
bd36216e8c
Use much more aggressive SpecAug setup
2022-02-08 21:55:20 +08:00
Daniel Povey
beaf5bfbab
Merge specaug change from Mingshuang.
2022-02-08 19:42:23 +08:00
Daniel Povey
395065eb11
Merge branch 'spec-augment-change' of https://github.com/luomingshuang/icefall into attention_relu_specaug
2022-02-08 19:40:33 +08:00
Wang, Guanbo
be1c86b06c
print num_frame as %.2f ( #204 )
2022-02-08 14:56:58 +08:00
Mingshuang Luo
3323cabf46
Experiments based on SpecAugment change
2022-02-08 14:25:31 +08:00
Fangjun Kuang
27fa5f05d3
Update git SHA-1 in RESULTS.md for transducer_stateless. ( #202 )
2022-02-07 18:45:45 +08:00
Fangjun Kuang
a8150021e0
Use modified transducer loss in training. ( #179 )
...
* Use modified transducer loss in training.
* Minor fix.
* Add modified beam search.
* Add modified beam search.
* Minor fixes.
* Fix typo.
* Update RESULTS.
* Fix a typo.
* Minor fixes.
2022-02-07 18:37:36 +08:00
Daniel Povey
a859dcb205
Remove learnable offset, use relu instead.
2022-02-07 12:14:48 +08:00
Wei Kang
35ecd7e562
Fix torch.nn.Embedding error for torch below 1.8.0 ( #198 )
2022-02-06 21:59:54 +08:00
Daniel Povey
48a764eccf
Add min in q,k,v of attention
2022-02-06 21:19:37 +08:00
Daniel Povey
8f8ec223a7
Changes to fbank computation, use lilcom chunky writer
2022-02-06 21:18:40 +08:00
pkufool
fcd25bdfff
Fix torch.nn.Embedding error for torch below 1.8.0
2022-02-06 18:22:56 +08:00
Wei Kang
5ae80dfca7
Minor fixes ( #193 )
2022-01-27 18:01:17 +08:00
Piotr Żelasko
8e6fd97c6b
Merge pull request #185 from pzelasko/feature/libri-conformer-phone-ctc
...
Fix using `lang_phone` in conformer CTC training
2022-01-24 18:08:15 -05:00
Piotr Żelasko
1731cc37bb
Black
2022-01-24 10:20:22 -05:00
Piotr Żelasko
f92c24a73a
Merge branch 'master' into feature/libri-conformer-phone-ctc
2022-01-24 10:18:56 -05:00
Piotr Żelasko
565c1d8413
Address code review
2022-01-24 10:17:47 -05:00
Piotr Żelasko
1d5fe8afa4
flake8
2022-01-21 17:27:02 -05:00
Piotr Żelasko
f0f35e6671
black
2022-01-21 17:22:41 -05:00
Piotr Żelasko
f28951f2b6
Add an assertion
2022-01-21 17:16:49 -05:00
Piotr Żelasko
3d109b121d
Remove train_phones.py and modify train.py instead
2022-01-21 17:08:53 -05:00
Fangjun Kuang
d6050eb02e
Fix calling optimized_transducer after new release. ( #182 )
2022-01-21 08:18:50 +08:00
Fangjun Kuang
f94ff19bfe
Refactor beam search and update results. ( #177 )
2022-01-18 16:40:19 +08:00
Fangjun Kuang
273e5fb2f3
Update git SHA1 for transducer_stateless model. ( #174 )
2022-01-10 11:58:17 +08:00
Fangjun Kuang
4c1b3665ee
Use optimized_transducer to compute transducer loss. ( #162 )
...
* WIP: Use optimized_transducer to compute transducer loss.
* Minor fixes.
* Fix decoding.
* Fix decoding.
* Add RESULTS.
* Update RESULTS.
* Update CI.
* Fix sampling rate for yesno recipe.
2022-01-10 11:54:58 +08:00
Piotr Żelasko
319e120869
Update feature config (compatible with Lhotse PR #525 ) ( #172 )
...
* Update feature config (compatible with Lhotse PR #525 )
* black
2022-01-10 11:39:28 +08:00
Lucky Wong
6caff5fd38
minor fixes ( #169 )
...
* Fix no attribute 'data' error.
* minor fixes
2022-01-06 10:24:16 +08:00
Daniel Povey
4314309f1e
Merge pull request #168 from huangruizhe/patch-1
...
Update make_kn_lm.py
2022-01-03 18:38:03 +08:00
huangruizhe
298faabb90
minor fixes
2022-01-02 23:38:33 -08:00
huangruizhe
7577b08bed
fixed the mistake
2022-01-02 23:32:43 -08:00
huangruizhe
82c8fac6ee
fixed a case where BOW can have problem to compute (ZeroDivisionError)
2022-01-02 15:29:50 -08:00
huangruizhe
0a67015d63
Update make_kn_lm.py
2022-01-02 00:27:27 -08:00
huangruizhe
49aab7e658
Update make_kn_lm.py
...
Fixed issue #163
2022-01-02 00:14:27 -08:00
pingfengluo
ea8af0ee9a
add transducer_stateless with char unit to AIShell ( #164 )
2022-01-01 18:32:08 +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
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
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
Fangjun Kuang
fb6a57e9e0
Increase the size of the context in the RNN-T decoder. ( #153 )
2021-12-23 07:55:02 +08:00
