7 Commits

Author SHA1 Message Date
Fangjun Kuang
1c9936898b Fix training. 2022-04-28 14:25:30 +08:00
Fangjun Kuang
026f446a4d Use k2 pruned RNN-T. 2022-04-28 14:13:26 +08:00
Fangjun Kuang
b0e4e5cf31 Minor fixes for decoding. 2022-04-28 10:39:08 +08:00
Fangjun Kuang
52b3ed2920 Use a stateless decoder for transducer_lstm. 2022-04-21 14:05:38 +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
1c35ae1dba
Reset seed at the beginning of each epoch. (#221)
* Reset seed at the beginning of each epoch.

* Use a different seed for each epoch.
2022-02-21 15:16:39 +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