 wenhongquan
|
ea42df876d
feat(llm-tts): streaming LLM + incremental TTS segmentation (xiaozhi pattern)
|
1 month ago |
 wenhongquan
|
2478295a00
fix(llm): use LLM_MODEL env var instead of hardcoded 'default'
|
1 month ago |
|
wenhongquan
|
1e97164777
rewrite(conversation-worker): full pipeline rewrite based on xiaozhi-esp32-server patterns
|
1 month ago |
|
wenhongquan
|
1059df76bc
fix(worker): use non-overlapping transcription window to eliminate duplicate outputs
|
1 month ago |
|
wenhongquan
|
a221c1ae02
fix(livekit): add participant_connected and track_published handlers to fix track_subscribed not firing
|
1 month ago |
|
wenhongquan
|
cee917bf35
refactor(transcript-proc): 重构转录处理器，支持批量返回处理结果
|
1 month ago |
|
wenhongquan
|
173eb24fc6
refactor: 重构语音识别转录处理逻辑，拆分前后端转录处理
|
1 month ago |
|
wenhongquan
|
01b300300b
feat(recording): add real-time speech-to-text display and finalize utterance logic
|
1 month ago |
|
wenhongquan
|
0b3247b701
chore: 移除websocket相关的调试打印日志
|
1 month ago |
|
wenhongquan
|
f05b0139b0
feat(macos+audio): 完善macOS端语音识别权限与音频传输逻辑
|
1 month ago |
|
wenhongquan
|
dc947bc293
feat: 完成全平台适配与功能迭代，新增报告页面与网络权限配置
|
1 month ago |
|
wenhongquan
|
6640ac014e
build(android): 配置阿里云maven镜像并替换gradle下载源
|
1 month ago |
|
wenhongquan
|
5a9f4e300a
feat: 初始化跨平台ASR客户端项目，添加基础工程与配置
|
1 month ago |
|
wenhongquan
|
0b259dbfd2
``
|
5 months ago |
|
wenhongquan
|
2373a412e3
``
|
5 months ago |
|
wenhongquan
|
fea1abeb4e
fix
|
5 months ago |
