This repository has been archived on 2026-03-23.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 907d28ca2a Make RMS loss dominate mean loss in Balancer if both are active; remove the 4x scale introduced in 814.

2023-01-01 00:09:14 +08:00

..

__init__.py

Merge changes from pruned_transducer_stateless4->5

2022-05-31 13:00:11 +08:00

asr_datamodule.py

Move pruned_transducer_stateless4 to pruned_transducer_stateless7

2022-05-31 12:45:28 +08:00

beam_search.py

Move pruned_transducer_stateless4 to pruned_transducer_stateless7

2022-05-31 12:45:28 +08:00

decode.py

Update decode.py by copying from pruned_transducer_stateless5 and changing directory name

2022-10-28 11:19:45 +08:00

decoder.py

Make decoder group size equal to 4.

2022-10-29 17:08:19 +08:00

encoder_interface.py

Move pruned_transducer_stateless4 to pruned_transducer_stateless7

2022-05-31 12:45:28 +08:00

export.py

Use decompose=True arg for model averaging

2022-05-31 14:28:53 +08:00

joiner.py

Adjust joiner and simple_lm/simple_am projections to account for larger activation dims

2022-12-29 12:52:11 +08:00

model.py

Adjust joiner and simple_lm/simple_am projections to account for larger activation dims

2022-12-29 12:52:11 +08:00

optim.py

Make sure param_rms limit is effectively applied; fix tests in optim.py

2022-12-29 23:55:16 +08:00

scaling.py

Make RMS loss dominate mean loss in Balancer if both are active; remove the 4x scale introduced in 814.

2023-01-01 00:09:14 +08:00

test_model.py

Merge changes from pruned_transducer_stateless4->5

2022-05-31 13:00:11 +08:00

train.py

Bug fix in save-bad-model code

2022-12-21 15:33:58 +08:00

zipformer.py

Increase max_abs of ZipformerEncoderLayer.balancer2 from 1.0 to 4.0.

2023-01-01 00:00:26 +08:00