Show HN: RealtimeVAD – trading false positives for 110ms earlier end-of-speech
Source: Show HN ·
Hey guys. I recently watched the latency reports for my local voice assistant, which show a waveform plus silero probability for voice activity. I noticed silero lags visibly on the speech off signal. There had to be a method to get this signal closer to what I felt is optimal. My idea was to use a 10 ms energy detector with a threshold that adapts to environment or room noise. Which worked amazingly well. It created more false positives but in my speculative generation pipeline that would not matter. If it's wrong and the user continues speaking I can abort the pipeline fast. I benchmarked my
Frequently Asked Questions
What is Show HN: RealtimeVAD – trading false positives for 110ms earlier end-of-speech?
Show HN: RealtimeVAD – trading false positives for 110ms earlier end-of-speech is a tool discovery curated from Show HN. Hey guys. I recently watched the latency reports for my local voice assistant, which show a waveform plus silero probability for voice activity. I noticed silero lags visibly on…
How can I access or experience this?
You can experience this content directly on its original host (Show HN) by clicking the "Open Original" button.
Where does this content come from?
Curated from Show HN by the OnSuggest team to surface the most interesting and serendipitous content on the web.
More like this
All Developer tools discoveries →Show HN: Lifetime Black Friday Deals (Mega List)
46 lifetime and one-time licenses with a Black Friday 2026 offer, each showing the discount, the code if there is one, and the dates it runs.
Show HN: A modern take on the Go language
Targets Go to use the toolchain and the package system you already know and love Comments URL: https://news.ycombinator.com/item?id=50595828 Points: 2 # Comments: 0
Show HN: Hikari.ImGui, a pure C# re-implementation of Dear ImGui
A pure, standalone C# re-implementation of the much-beloved and widely used immediate-mode GUI for 3D applications, Dear ImGui, targeting version v1.93.0-docking with zero native dependencies. Please feel free to use for your projects. Also available as a nuget package. Comments URL: https://news.ycombinator.com/item?id=50595885 Points: 2 # Comments: 0
Show HN: System 1.5 Model – Inkling-2-Mini Decision
Feature Extraction model with 26B parameters. Download, explore files and run it on Hugging Face.
Show HN: GitHub Plays Linux
A few years ago, my GitHub profile README was more or less a livestream of my personal projects since I liked the idea of working in the open. It essentially embedded an image served from a small VPS with caching disabled, and my machine kept uploading screenshots of the workspace I used for those projects. So visitors saw whatever I was building at that moment. I wanted to bring that back in a form where visitors can take part rather than just watch. The README now has a terminal attached to a small Linux VM on my VPS and every visitor types into the same machine. READMEs can't run scripts, s
Show HN: Vouch – See what AI assistants say about your brand mid-conversation
Vouch is a generative engine optimisation tool that shows how AI assistants talk about your brand across a whole buying conversation, and where you drop out.