perf(asr): speed up local Flow dictation and land CLM/keyboard refactor
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:
@@ -29,7 +29,7 @@ struct PrepareOptions {
|
||||
.deletingLastPathComponent()
|
||||
|
||||
var input = repoRoot.appendingPathComponent(
|
||||
"OSGKeyboard/Resources/CustomLanguageModel/v1/OSGKeyboardCLM.bin"
|
||||
"OSGKeyboardShared/Resources/CustomLanguageModel/v1/OSGKeyboardCLM.bin"
|
||||
)
|
||||
var output = repoRoot.appendingPathComponent(
|
||||
"OSGKeyboard/Resources/CustomLanguageModel/v1/compiled"
|
||||
|
||||
Reference in New Issue
Block a user