perf(asr): speed up local Flow dictation and land CLM/keyboard refactor

Browse Source

Reduce perceived latency from key release to final text:
- Adaptive chunking: 2.5s first chunk + 5s follow-ups so short
  utterances start on-device recognition while still recording.
- Session-level ASR warmup and audio-format cache reuse to remove
  per-utterance cold-start of SpeechAnalyzer.
- Mirror live pipelined partials to the keyboard transcript line via
  a new flow.transcriptionPartial App Group key + Darwin ping.

Also commits the accumulated custom language model, Flow session,
keyboard extension restructure, and Xiaomi MiMo provider work in
progress on this branch.

...

This commit is contained in:

Rocky

2026-07-06 00:00:19 +08:00

parent cfbfb542cc

commit 537a68552a

76 changed files with 3456 additions and 121086 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

OSGKeyboardShared/Resources/CustomLanguageModel/v1/OSGKeyboardCLM.bin

BIN

Binary file not shown.