Fangjun Kuang
4159d6fbf6
Merge remote-tracking branch 'dan/master' into rnnt-modified
2022-02-07 16:43:14 +08:00
Fangjun Kuang
45866f95b4
Minor fixes.
2022-02-07 16:39:39 +08:00
Fangjun Kuang
e614e0bd45
Fix a typo.
2022-02-07 16:32:28 +08:00
Fangjun Kuang
3b93761199
Update RESULTS.
2022-02-07 16:31:10 +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
Fangjun Kuang
534cac4406
Minor fixes.
2022-01-29 12:59:01 +08:00
Fangjun Kuang
77261bc575
Add modified beam search.
2022-01-28 23:51:04 +08:00
Fangjun Kuang
c3b3123b27
Add modified beam search.
2022-01-28 16:20:42 +08:00
Wei Kang
5ae80dfca7
Minor fixes ( #193 )
2022-01-27 18:01:17 +08:00
Fangjun Kuang
50eb78566b
Minor fix.
2022-01-21 11:22:24 +08:00
Fangjun Kuang
d6050eb02e
Fix calling optimized_transducer after new release. ( #182 )
2022-01-21 08:18:50 +08:00
Fangjun Kuang
92e524ea7f
Use modified transducer loss in training.
2022-01-20 11:34:00 +08:00
Fangjun Kuang
f94ff19bfe
Refactor beam search and update results. ( #177 )
2022-01-18 16:40:19 +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
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
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
