d3ro-voice/apps
Yun Chan 8d003c8fca fix(caption): unload the caption-only STT model when a start is cancelled or fails
stop() during model loading saw no aux model yet and skipped the unload, and
the failure path (e.g. no microphone) never unloaded it, so the caption model
kept VRAM alongside the dictation model until the next session ended.
2026-10-21 00:25:35 +09:00
..
admin chore(release): v1.10.0 2026-10-18 07:07:46 +09:00
admin-swagger chore(release): v1.10.0 2026-10-18 07:07:46 +09:00
api-server chore(release): v1.10.0 2026-10-18 07:07:46 +09:00
api-server.Tests feat(release): prepare 1.1.0 candidate 2026-08-29 18:33:45 +09:00
desktop fix(caption): unload the caption-only STT model when a start is cancelled or fails 2026-10-21 00:25:35 +09:00
mobile-rn chore(release): v1.10.0 2026-10-18 07:07:46 +09:00
web chore(release): v1.10.0 2026-10-18 07:07:46 +09:00