mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 10:02:22 +00:00
Code Issues Packages Projects Releases Wiki Activity
icefall/egs/librispeech/ASR
History
Fangjun Kuang a8150021e0
Use modified transducer loss in training. (#179) 
* Use modified transducer loss in training.

* Minor fix.

* Add modified beam search.

* Add modified beam search.

* Minor fixes.

* Fix typo.

* Update RESULTS.

* Fix a typo.

* Minor fixes.
2022-02-07 18:37:36 +08:00
..
conformer_ctc
Black
2022-01-24 10:20:22 -05:00
conformer_mmi
Set fsa.properties to None after changing its labels in-place. (#121)
2021-11-16 23:11:30 +08:00
local
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
tdnn_lstm_ctc
Associate a cut with token alignment (without repeats) (#125)
2021-11-29 18:50:54 +08:00
transducer
Fix torch.nn.Embedding error for torch below 1.8.0 (#198)
2022-02-06 21:59:54 +08:00
transducer_lstm
Fix torch.nn.Embedding error for torch below 1.8.0 (#198)
2022-02-06 21:59:54 +08:00
transducer_stateless
Use modified transducer loss in training. (#179)
2022-02-07 18:37:36 +08:00
prepare.sh
Add MMI training with word pieces as modelling unit. (#6)
2021-10-18 15:20:32 +08:00
README.md
Increase the size of the context in the RNN-T decoder. (#153)
2021-12-23 07:55:02 +08:00
RESULTS.md
Use modified transducer loss in training. (#179)
2022-02-07 18:37:36 +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 Embedding + Conv1d
transducer_lstm LSTM LSTM

The decoder in transducer_stateless is modified from the paper Rnn-Transducer with Stateless Prediction Network. We place an additional Conv1d layer right after the input embedding layer.