7 Commits

Author	SHA1	Message	Date
pkufool	08729f88b1	Fix the mismatch of forward & backward joiner label	2022-01-28 18:21:15 +08:00
pkufool	18f997fe51	Fix bugs in backward decoder	2022-01-27 17:34:44 +08:00
pkufool	8b7f43a027	Add backward decoder	2022-01-26 14:27:41 +08:00
pkufool	f4b8b0641a	Replace torchaudio rnnt_loss to k2 pruned rnnt loss	2022-01-07 13:02:46 +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