split and process valid set #25
Merged
Conversation
This file contains 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
lmxue
requested review from
RMSnow,
zhizhengwu,
HeCheng0625 and
VocodexElysium
RMSnow
requested changes
Dec 12, 2023
There was a problem hiding this comment.
What will happen when processing other datasets except for libritts and ljspeech? I suspect that line39 will cause a bug, since there is none valid.json for others.
Besides, is there any corresponding design for the valid and test dataset in trainer?
There was a problem hiding this comment.
Rewrite metadata.py to automatically adapt different json files.
The valid set is split to distinguish it from the test set and also used to compute validation loss in the trainer.
RMSnow
requested changes
Dec 14, 2023
preprocessors/metadata.py
Outdated
| @@ -8,7 +8,7 @@ | |||
| from tqdm import tqdm | |||
|
|
|||
|
|
|||
| def cal_metadata(cfg): | |||
| def cal_metadata(cfg, dataset_types): | |||
There was a problem hiding this comment.
For SVC, TTA, and Vocoder, the existing calls to this funcion is cal_metadata(cfg). So the implementation here will cause a bug. Maybe you can set default values to dataset_types.
RMSnow
approved these changes
Dec 14, 2023
This was referenced Dec 14, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
The PR is to support the validation set split and process to standardize the dataset.