pkufool
85ddfd958c
Minor fixes
2022-06-10 19:06:06 +08:00
pkufool
d7be9bd9c5
Minor fixes
2022-06-07 12:00:26 +08:00
pkufool
1c794e32b0
Minor fixes
2022-06-06 20:19:49 +08:00
pkufool
09b0c54983
Minor fixes
2022-06-06 17:56:22 +08:00
pkufool
3aacf75652
fix relative positional encoding in streaming decoding for compution saving
2022-06-06 06:46:40 +08:00
pkufool
0325e3a04e
Add torch.jit.export
2022-05-29 16:25:01 +08:00
pkufool
aecaecfb17
Fix style
2022-05-29 07:35:52 +08:00
pkufool
b23db42486
Fix conv cache error, support async streaming decoding
2022-05-29 07:06:44 +08:00
pkufool
364bccb2e3
Merge branch 'master' into streaming-conformer
2022-05-26 10:29:08 +08:00
pkufool
7cc697c03a
support streaming on pruned_transducer_stateless2; add delay penalty; fixes for decode states
2022-05-22 17:14:17 +08:00
pkufool
118b09463d
Add more documents
2022-05-20 15:26:45 +08:00
pkufool
5bd2490b44
support streaming in conformer
2022-05-18 23:26:24 +08:00
Fangjun Kuang
f6ce135608
Various fixes to support torch script. ( #371 )
...
* Various fixes to support torch script.
* Add tests to ensure that the model is torch scriptable.
* Update tests.
2022-05-16 21:46:59 +08:00
Fangjun Kuang
9a11808ed3
Set the seed for dataloader. ( #282 )
...
Also, suppress torch warnings about division by truncation.
2022-03-31 16:48:46 +08:00
Fangjun Kuang
1603744469
Refactor conformer. ( #237 )
2022-03-05 19:26:06 +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
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
