创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

作者重构自托管语音助手管线

AI 总结

一名开发者使用新的 assistant.microwakeword 插件重构了基于 Platypush 的自托管语音助手管线,并以 assistant.openai 完成 Whisper 转写、由 openai 插件处理回答和上下文,再用 tts.openai 合成语音。共享音频预处理层现支持 Silero、WebRTC 和能量 VAD,并加入迟滞、平滑窗口及自适应噪声底;作者在合成基准中称,语音结束检测由末词后 6–10 秒缩短至 1.0–1.6 秒。

深度见解

该项目提供了构建更稳健自托管 AI 语音栈的具体实现、配置和代码改动,但其基准及默认参数仅由作者在合成音频和少量个人录音上测试。

I wrote an article a couple of months ago describing how I rebuilt my old voice assistant pipeline in Platypush.

And I wrote earlier articles describing my journey through self-hosted voice assistants - in 2024 (with Picovoice), in 2020 (diving into the legacy assistant.google integration, the now defunct assistant.alexa integration, the now defunct Snowboy integration, the now defunct DeepSpeech integration and Picovoice) and the original article in 2019 describing the Google Assistant integration.

For a couple of months I used the voice pipeline described in my latest article as my main driver, but after getting used to the robustness of commercial voice assistants I was unhappy with the high rates of false positives/negatives of my self-hosted pipeline, as well as its lack of robustness in detecting start/end of speech, especially in noisy environments and using cheap microphones.

#Platypush#assistant.microwakeword#microWakeWord#OpenAI#Whisper#Silero VAD#ESPHome#Home Assistant Voice#Ollama#Piper#TTS

原文约 6 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。