open-standards/aac/aac-rs/third_party
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Transaction Science 9ae455a99b Merge origin/main into aac/voice-quality: bar scanning, First letters, the hotfix
No textual conflicts. One rate-and-pitch persistence mechanism, not two:
main's profile sync (71a804f3, the access method, motor profile, vocabulary
level and voice, once the saved state is in) already saves the voice, so
this branch's own voice-only effect is dropped. The README's voice line now
describes the simpler rule (the best device voice speaks; robotic ones last).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-04 20:15:01 -04:00
..
hf-tokenizers fix(aac first letters): a model let go holds the chip until it has; checks never wait for each other 2026-10-02 00:51:00 -04:00
litert-lm feat(aac sentence helper): whole sentences and replies, suggested on the device 2026-10-01 06:52:48 -04:00
mediapipe feat(aac-web): same-origin MediaPipe, a capability probe, a model store 2026-09-29 10:50:19 -04:00
moonshine-wasm feat(aac-web): better voices, on the device, in 11 languages 2026-09-30 18:23:13 -04:00
onnxruntime-web fix(aac listener): its worker owns its GPU device, and gives it back before it ends 2026-10-02 00:47:11 -04:00
readium-speech feat(access-core): rank device voices by quality, and name the ones never to use 2026-10-04 15:06:20 -04:00