Downloads · 30 days
0
duckking032/vital-jepa-v5
vital-jepa-v5 is a machine learning model from duckking032. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as other.
V5 extends the feature-focused V4 encoder with exact, single-control interventions rendered by Vital 1.6.4. Its main goal is to preserve acoustic state while making synthesizer-control effects accessible to a downstre…
Downloads · 30 days
0
Access
Public
Updated Jul 11, 2026
Repo size
146 MB
Likes
0
Public
Click a slice to open those files.
.pt146 MB · 100%
From the Hugging Face model README
V5 extends the feature-focused V4 encoder with exact, single-control interventions rendered by Vital 1.6.4. Its main goal is to preserve acoustic state while making synthesizer-control effects accessible to a downstream preset decoder.
The dataset is stored under
interventions_v5_22050_stereo_6s/ in duckking032/vital. Every accepted
intervention records its exact control ID, before/after values, signed delta,
magnitude, and direction.
Training ran for 10 epochs / 20,440 steps in 2,451 seconds. Checkpoint 15,000 was selected by the held-out control, acoustic, and retrieval comparison.
| Metric | Result |
|---|---|
| Mean acoustic descriptor correlation | 0.8499 |
| Mean acoustic descriptor MAE | 0.0419 |
| Acoustic-delta cosine | 0.2536 |
| Built-in 40-way control accuracy | 15.52% |
| Built-in control-sign accuracy | 62.59% |
| Built-in control-effect cosine | 0.1996 |
| Coarse retrieval top-1 | 43.79% |
| Coarse retrieval top-5 | 62.20% |
| Coarse MRR@10 | 0.5157 |
Chance accuracy is 2.5% for control identity and 50% for direction.
Probes use 2,000 training parents and fully disjoint validation/test parents; the JEPA remains frozen.
| Probe | Linear | MLP |
|---|---|---|
| Acoustic descriptor correlation | 0.8253 | 0.8408 |
| Acoustic-delta correlation | 0.6003 | 0.6015 |
| 40-way control accuracy | 20.75% | 34.84% |
| 40-way balanced accuracy | 13.38% | 25.14% |
| Control-direction balanced accuracy | 70.70% | 72.94% |
The gap between the built-in control head and the frozen MLP probe shows that the encoder contains substantially more control information than the small training head extracts. This is encouraging for a learned preset decoder.
Control information is uneven. Envelope controls and several on/off effects
are much easier than oscillator-2/3 and subtle spectral/unison parameters.
Control-direction centroid consistency is still modest (mean cosine 0.117),
and the encoder does not itself produce a complete .vital preset.
checkpoints/jepa_v5/selected.pt is the optimizer-free selected checkpoint.
The full evaluation, checkpoint comparison, and probe report are included.