Daniel Povey 71b3756ada Use half the dim per head, in self_attn layers.

2022-09-24 15:40:44 +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

conformer.py

Use half the dim per head, in self_attn layers.

2022-09-24 15:40:44 +08:00

decode.py

Remove decompose=True

2022-06-03 11:48:45 +08:00

decoder.py

Patches to make decoding work correctly at utt start, for greedy_search

2022-07-27 09:35:39 +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

Move pruned_transducer_stateless4 to pruned_transducer_stateless7

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

model.py

Move pruned_transducer_stateless4 to pruned_transducer_stateless7

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

optim.py

Fix issues where grad is None, and unused-grad cases

2022-09-22 19:18:16 +08:00

scaling.py

Reduce debug freq

2022-09-22 12:30:49 +08:00

test_model.py

Merge changes from pruned_transducer_stateless4->5

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

train.py

Configure train.py with clipping_scale=2.0

2022-09-16 17:19:52 +08:00