Ethanfel 78e9838a83 fix: replace peak normalization with RMS normalization at -20 dBFS ...

Peak norm was slamming output to full scale regardless of content level,
making generated audio several times louder than training clips.
RMS norm to -20 dBFS matches typical processed audio level.
Sampler exposes target_lufs (-40 to -6, default -20) for user control.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-08 12:06:48 +02:00

..

__init__.py

feat: add SelVA Dataset Browser node

2026-04-07 14:55:27 +02:00

selva_dataset_browser.py

feat: thorough overnight sweep + dataset browser updates

2026-04-08 00:38:19 +02:00

selva_feature_extractor.py

fix: set OUTPUT_NODE=True on SelVA Feature Extractor so it runs without connected outputs

2026-04-06 00:11:16 +02:00

selva_lora_loader.py

debug: print lora_A norm after loading to confirm adapter applied

2026-04-05 23:05:23 +02:00

selva_lora_scheduler.py

feat: sweep resume + 5 additional experiments (LR, target, extended)

2026-04-08 00:59:16 +02:00

selva_lora_trainer.py

fix: replace peak normalization with RMS normalization at -20 dBFS

2026-04-08 12:06:48 +02:00

selva_model_loader.py

feat: comprehensive node improvements

2026-04-04 18:16:03 +02:00

selva_sampler.py

fix: replace peak normalization with RMS normalization at -20 dBFS

2026-04-08 12:06:48 +02:00

utils.py

chore: remove all PrismAudio code from main branch

2026-04-04 17:58:31 +02:00