icefall

mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-08 09:32:20 +00:00

History

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

local

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

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

tdnn

RNN-T training for yesno. (#141 )

2021-12-07 21:44:37 +08:00

transducer

RNN-T Conformer training for LibriSpeech (#143 )

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

prepare.sh

Use LossRecord to record and print the loss for the training process (#62 )

2021-10-12 15:58:03 +08:00

README.md

Add documentation about code style and creating new recipes. (#27 )

2021-08-25 14:48:41 +08:00

shared

Add recipe for the yes_no dataset. (#16 )

2021-08-23 11:36:29 +08:00

README.md

Yesno recipe

This is the simplest ASR recipe in icefall.

It can be run on CPU and takes less than 30 seconds to get the following WER:

[test_set] %WER 0.42% [1 / 240, 0 ins, 1 del, 0 sub ]

Please refer to https://icefall.readthedocs.io/en/latest/recipes/yesno.html for detailed instructions.