fix: resolve bugs in WarmupLR_withStepDecay and train config #446
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
cdliang11
reviewed
Dec 30, 2025
wespeaker/bin/extract.py
Outdated
|
|
||
| # apply cmvn | ||
| if test_conf.get('cmvn', True): | ||
| if test_conf.get('cmvn', False): |
Collaborator
There was a problem hiding this comment.
其他任务上默认cmvn是开的，为了保持兼容性，这里建议通过配置文件指定cmvn = false
wespeaker/utils/executor.py
Outdated
| with torch.cuda.amp.autocast(enabled=configs['enable_amp']): | ||
| # apply cmvn | ||
| if configs['dataset_args'].get('cmvn', True): | ||
| if configs['dataset_args'].get('cmvn', False): |
cdliang11
approved these changes
Dec 31, 2025
Closed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR fixes two issues in the training configuration and scheduler:
WarmupLR_withStepDecay:
warmup_stepwas treated as iterations instead of epochs. It is now correctly multiplied byepoch_iter.Config Compatibility:
train.pyto use.pop('initial_lr'). This preventsKeyError/TypeErrorwheninitial_lris not defined inscheduler_args(e.g., in W2V tasks), while maintaining compatibility for other tasks.CMVN Default:
executor.py.