Ethanfel fec5c86f09 feat: add spectral_flatness and temporal_variance to eval metrics ...

spectral_flatness (Wiener entropy) — 0=tonal, 1=white noise.
Rising value across steps directly flags noise contamination.
temporal_variance — RMS std/mean per frame. Low = lifeless/compressed.

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

2026-04-08 12:45:40 +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: spectral metrics per eval sample in experiment summary

2026-04-08 12:44:43 +02:00

selva_lora_trainer.py

feat: add spectral_flatness and temporal_variance to eval metrics

2026-04-08 12:45:40 +02:00

selva_model_loader.py

feat: comprehensive node improvements

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

selva_sampler.py

fix: prevent saturation from RMS normalization clipping peaks

2026-04-08 12:29:29 +02:00

utils.py

chore: remove all PrismAudio code from main branch

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