2026-09-05 報 release. 5 September 2026

Semantic models cover 22 languages

The models registry grows from 9 to 22 languages, with thirteen new FastText reranking tiers shipped behind the same eval gates.

Registry v1.1.0 adds ca, cs, da, el, hu, it, nl, pl, ro, sv, tr, uk, and vi — every batch-one language whose dictionary exists — for a total of 22 languages × 3 tiers, 66 registry resources.
The gates did not move: every fluency tier holds rank correlation 0.9999 with top-1 of at least 0.958, every mini tier is near-lossless, and a language that fails its gates ships nothing.
The keyboard-aware eval grew with them — QWERTY/QWERTZ supplements plus curated Turkish-Q, Ukrainian ЙЦУКЕН, and Greek-phonetic noise grids — so newcomer languages are judged on their own keyboards.
The released registry.json is byte-identical to the committed one: local rebuilds reproduce the CI sha256 exactly, so future expansions are verifiable, not trusted.