Uh oh!
There was an error while loading. Please reload this page.
feat(mixln): add config switch to disable speaker-shuffle during training - #326
Open
KakaruHayate wants to merge 3 commits into
Open
feat(mixln): add config switch to disable speaker-shuffle during training#326KakaruHayate wants to merge 3 commits into
KakaruHayate wants to merge 3 commits into
Conversation
…ning Mixed_LayerNorm mixes affine (beta/gamma) params across shuffled speakers in the batch at training time. Add a mixln_shuffle_speakers flag (default true = original behaviour) that keeps the conditional-affine network structure but skips the speaker shuffle when set to false, so each speaker's params stay consistent within a step (less inter-speaker leakage). The flag is threaded constructor-to-constructor (no new hparams imports in layer modules, per repo convention) and synced into both acoustic configs.
KakaruHayate added a commit
to KakaruHayate/DiffSinger
that referenced
this pull request
Aug 25, 2026
# Conflicts: # configs/acoustic.yaml # configs/templates/config_acoustic.yaml # modules/commons/common_layers.py # modules/fastspeech/acoustic_encoder.py # modules/fastspeech/tts_modules.py
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
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Mixed_LayerNorm mixes affine (beta/gamma) params across shuffled speakers in the batch at training time. Add a \mixln_shuffle_speakers\ flag (default: disabled) that keeps the conditional-affine network structure but skips the speaker shuffle when set to false, so each speaker's params stay consistent within a step (less inter-speaker leakage).
The flag is threaded constructor-to-constructor (no new hparams imports in layer modules, per repo convention) and synced into both acoustic configs.
Source: KakaruHayate/DiffSinger default branch commit c10fd2e (merge of #63).