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/wenetspeech/ASR
History
fanlu 8a3068ead8
Update decode.py (#392) 
* Update decode.py

fix bug ```TypeError: greedy_search_batch() missing 1 required positional argument: 'encoder_out_lens'```

* fix modified_beam_search

Co-authored-by: fanlu3 <fanlu@jd.com>
2022-06-04 19:08:17 +08:00
..
local
[egs] Add prefix when reading manifests due to recent lhotse changes (#382)
2022-05-23 23:37:35 +08:00
pruned_transducer_stateless2
Update decode.py (#392)
2022-06-04 19:08:17 +08:00
prepare.sh
[Ready to merge] Pruned Transducer Stateless2 for WenetSpeech (char-based) (#349)
2022-05-23 17:13:01 +08:00
README.md
[Ready to merge] Pruned Transducer Stateless2 for WenetSpeech (char-based) (#349)
2022-05-23 17:13:01 +08:00
RESULTS.md
[Ready to merge] Pruned Transducer Stateless2 for WenetSpeech (char-based) (#349)
2022-05-23 17:13:01 +08:00
shared
[Ready to merge] Pruned Transducer Stateless2 for WenetSpeech (char-based) (#349)
2022-05-23 17:13:01 +08:00

README.md

Introduction

This recipe includes some different ASR models trained with WenetSpeech.

./RESULTS.md contains the latest results.

Transducers

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

Encoder Decoder Comment
pruned_transducer_stateless2 Conformer(modified) Embedding + Conv1d Using k2 pruned RNN-T loss

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.