Daniel Povey 9e86d1f44f reduce initial scale in GradScaler

2022-10-23 00:14:38 +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

Increase default max_factor for ActivationBalancer from 0.02 to 0.04; decrease max_abs in ConvolutionModule.deriv_balancer2 from 100.0 to 20.0

2022-10-23 00:09:21 +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

don't do penalize_values_gt on simple_lm_proj and simple_am_proj; reduce --base-lr from 0.1 to 0.075

2022-10-22 21:12:58 +08:00

optim.py

Renaming in optim.py; remove step() from scan_pessimistic_batches_for_oom in train.py

2022-10-22 17:44:21 +08:00

scaling.py

Increase default max_factor for ActivationBalancer from 0.02 to 0.04; decrease max_abs in ConvolutionModule.deriv_balancer2 from 100.0 to 20.0

2022-10-23 00:09:21 +08:00

test_model.py

Merge changes from pruned_transducer_stateless4->5

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

train.py

reduce initial scale in GradScaler

2022-10-23 00:14:38 +08:00