feat(semantics): validated CLAP vibe-search + live /vibe endpoint (#82,#86)
Katana-first finding: per-one-shot CLAP genre/mood tags are unreliable (every hit → boom-bap/euphoric — a 0.3s sound has no genre), but the audio EMBEDDINGS are gold for RELATIVE similarity. 'warm dusty rhodes' → suns_keys gold-keys + west-coast electric; 'jazzy upright bass' → no_sunshine/come_bass loops; a kick's nearest neighbours are other kicks (0.96 cross-folder). So we ship similarity, not fake absolute labels (Principle 1: trust the instrument). - sample_semantics.py validated on real audio; semantics_embeds.npz = 1490×512-d. - serve.py: lazy CLAP /vibe?q= (embed any phrase → rank) + /similar?name= (by audio-embed cosine). 503 if unbuilt, 400/404 on bad input; static serving untouched. Single-user LAN, torch loads once on first hit.
Showing
armada/tide-table/sample_semantics.py
0 → 100644
This diff is collapsed.
Click to expand it.
armada/tide-table/semantics_embeds.npz
0 → 100644
File added
Please
register
or
sign in
to comment