icefall/egs/librispeech/ASR/pruned_transducer_stateless7_streaming
LoganLiu66 f08af2fa22
fix initial states (#1398)
Co-authored-by: liujiawang02 <liujiawang02@baidu.com>
2023-12-04 22:29:42 +08:00
..
2022-12-30 10:52:18 +08:00
2023-12-04 22:29:42 +08:00
2022-12-30 10:52:18 +08:00
2023-06-02 14:12:42 +08:00
2022-12-30 10:52:18 +08:00
2022-12-30 10:52:18 +08:00
2023-09-21 21:16:14 +08:00
2022-12-30 10:52:18 +08:00
2022-12-30 10:52:18 +08:00
2023-06-21 17:17:19 +08:00
2023-09-21 19:41:10 +08:00

This recipe implements Streaming Zipformer-Transducer model.

See https://k2-fsa.github.io/icefall/recipes/Streaming-ASR/librispeech/zipformer_transducer.html for detailed tutorials.

./emformer.py and ./train.py are basically the same as ./emformer2.py and ./do_not_use_it_directly.py. The only purpose of ./emformer2.py and ./do_not_use_it_directly.py is for exporting to sherpa-ncnn.