icefall/egs/librispeech/ASR/pruned_transducer_stateless7_streaming
marcoyang1998 34d1b07c3d
Modified beam search with RNNLM rescoring (#1002)
* add RNNLM rescore

* add shallow fusion and lm rescore for streaming zipformer

* minor fix

* update RESULTS.md

* fix yesno workflow, change from ubuntu-18.04 to ubuntu-latest
2023-04-17 16:43:00 +08:00
..
2022-12-30 10:52:18 +08:00
2022-12-30 10:52:18 +08:00
2022-12-30 10:52:18 +08:00
2022-12-30 10:52:18 +08:00
2023-02-07 15:01:59 +08:00
2022-12-30 10:52:18 +08:00
2022-12-30 10:52:18 +08:00
2022-12-30 10:52:18 +08:00
2023-03-08 22:56:04 +08:00
2022-12-30 10:52:18 +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 ./train2.py. The only purpose of ./emformer2.py and ./train2.py is for exporting to sherpa-ncnn.