merge: tail-drain and chunked ASR hardening into main
Resolve FlowContinuousCapture by combining tail-drain gate/drain logic with flow-abcd route-change and interruption recovery.
This commit is contained in:
@@ -19,6 +19,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
### Changed
|
||||
- **Keyboard language label**: `PrimaryLanguage` set to `mis` so Settings no longer shows a misleading “English” subtitle under OSGKeyboard. / **键盘语言标签**:`PrimaryLanguage` 设为 `mis`,系统设置中 OSGKeyboard 下不再显示误导性的「英文」副标题。
|
||||
- **Flow ASR pipelining**: shorter first chunk (2.5s) and 5s follow-ups so short utterances start on-device recognition while still recording; session-level ASR warmup and format cache reuse; live partials mirrored to the keyboard transcript line. / **Flow ASR 流水线**:首块 2.5 秒、后续 5 秒,短句录音期间即开始端侧识别;会话级 ASR 预热与格式缓存复用;实时 partial 同步到键盘转写行。
|
||||
- **Flow tail drain**: after mic stop, capture drains trailing PCM (silence-detected, capped) before finishing the ASR stream; host finalize awaits drain; short final chunks re-transcribed with prior overlap; stitcher safe fallback when overlap merge would drop content. / **Flow 尾音排空**:停止录音后先排空尾部 PCM(静音检测 + 上限)再结束 ASR 流;主 App finalize 等待排空;过短末块与上一块 overlap 合并重识别;拼接误删时回退为安全合并。
|
||||
|
||||
## [0.4.0] - 2026-07-05
|
||||
|
||||
|
||||
Reference in New Issue
Block a user