mirrors/icefall

mirror of https://github.com/k2-fsa/icefall.git synced 2025-12-09 22:15:28 +00:00

History

Fangjun Kuang 7f4749a4d6 Fix CI errors.

2021-12-22 15:26:26 +08:00

..

RNN-T Conformer training for LibriSpeech (#143 )

2021-12-18 07:42:51 +08:00

Set fsa.properties to None after changing its labels in-place. (#121 )

2021-11-16 23:11:30 +08:00

RNN-T Conformer training for LibriSpeech (#143 )

2021-12-18 07:42:51 +08:00

streaming_conformer_ctc

Draft streaming decoding (#89 )

2021-11-24 19:35:18 +08:00

Associate a cut with token alignment (without repeats) (#125 )

2021-11-29 18:50:54 +08:00

Limit the number of symbols per frame in RNN-T decoding. (#151 )

2021-12-18 11:00:42 +08:00

transducer_lstm

Limit the number of symbols per frame in RNN-T decoding. (#151 )

2021-12-18 11:00:42 +08:00

transducer_stateless

Fix CI errors.

2021-12-22 15:26:26 +08:00

prepare.sh

Add MMI training with word pieces as modelling unit. (#6 )

2021-10-18 15:20:32 +08:00

README.md

Fix CI errors.

2021-12-22 15:26:26 +08:00

RESULTS.md

Implement beam search.

2021-12-22 15:15:58 +08:00

shared

Refactoring (#4 )

2021-08-04 14:53:02 +08:00

README.md

Introduction

Please refer to https://icefall.readthedocs.io/en/latest/recipes/librispeech.html for how to run models in this recipe.

Transducers

There are various folders containing the name transducer in this folder. The following table lists the differences among them.

	Encoder	Decoder
`transducer`	Conformer	LSTM
`transducer_stateless`	Conformer	Conv1d + Embedding
`transducer_lstm`	LSTM	LSTM