2026-09-05 報 release. 5 September 2026

Semantic models cover 54 languages

The models registry grows from 22 to 54 languages, with 32 new languages shipped including the first right-to-left languages, behind unchanged eval gates.

Registry v1.2.0 ships 32 new languages × 3 tiers for a total of 54 languages and 162 registry resources. Arabic, Persian, and Hebrew arrive as the registry’s first right-to-left languages, with new dictionaries verified against upstream license headers where none existed.
The gates did not move, with fluency held at rank correlation 0.97 and top-1 0.95 and mini at 0.90 and 0.85, never weakened, and the whole batch clears them comfortably, with fluency at 0.9999 to 1.0000 correlation and mini near-lossless. The keyboard-aware evaluation grew ten more curated national grids so the newcomer languages are judged on their own keyboards.
Not everything that converts ships. The nds language passed both gates but is ISO 639-2 only, while the registry’s language contract is two-letter codes; fi has no license-clear Hunspell source upstream; and fo, rw, ie, fur, and tlh have no fastText Common Crawl vectors at all. Every drop is recorded with its reason in the README.
The candidate pool is now exhausted: every convertible language either ships or is dropped for a stated reason, so the coverage backlog is empty. What remains, namely the no→nb/nn alias, fi sourcing, and the nds Resource Spec call, is an owner decision rather than pending work.