This repository has been archived on 2026-03-23. You can view files and clone it, but cannot push or open issues or pull requests.

Daniel Povey d2d0ce0335 Try to get rid of gradient blowup

2023-05-15 20:26:21 +08:00

..

chunk_decoder.py

Fix DDP issue; Change configurations, reducing subsampling factor; increase sequence length.

2023-05-04 16:18:31 +08:00

decoder.py

First version of subformer that runs.

2023-05-15 16:03:01 +08:00

encoder_interface.py

Initial version of zipformer1 LM that runs, not sure whether it is working

2023-05-04 14:46:06 +08:00

lm_datamodule.py

Fix DDP issue; Change configurations, reducing subsampling factor; increase sequence length.

2023-05-04 16:18:31 +08:00

model.py

First version of subformer that runs.

2023-05-15 16:03:01 +08:00

optim.py

Initial version of zipformer1 LM that runs, not sure whether it is working

2023-05-04 14:46:06 +08:00

scaling.py

Initial version of zipformer1 LM that runs, not sure whether it is working

2023-05-04 14:46:06 +08:00

subformer.py

Try to get rid of gradient blowup

2023-05-15 20:26:21 +08:00

train.py

Reduce batch size slightly

2023-05-15 20:13:48 +08:00