<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ml on jason grey</title><link>https://jason-grey.com/tags/ml/</link><description>Recent content in Ml on jason grey</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 27 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://jason-grey.com/tags/ml/index.xml" rel="self" type="application/rss+xml"/><item><title>Live Translation Subtitles on Linux with PipeWire and a GPU</title><link>https://jason-grey.com/posts/2026/translation-overlay/</link><pubDate>Fri, 27 Mar 2026 00:00:00 +0000</pubDate><guid>https://jason-grey.com/posts/2026/translation-overlay/</guid><description>&lt;p&gt;I am working with more Spanish-speaking folks lately — and wanted live subtitles without routing audio through a cloud service. So I built a hack.&lt;/p&gt;
&lt;p&gt;&lt;a href="https://github.com/jt55401/translation-overlay" class="external-link" target="_blank" rel="noopener"&gt;translation-overlay&lt;/a&gt; captures system audio from PipeWire, pipes it through a local translation model, and renders the output as floating subtitles on top of all windows.&lt;/p&gt;
&lt;pre tabindex="0"&gt;&lt;code&gt;System Audio → PipeWire capture → ML translation engine → Subtitle overlay
&lt;/code&gt;&lt;/pre&gt;&lt;p&gt;It&amp;rsquo;s two Python scripts duct-taped together with a shell wrapper. &lt;code&gt;caption_engine.py&lt;/code&gt; grabs audio from your default PipeWire sink monitor via &lt;code&gt;pw-record&lt;/code&gt;, runs it through one of three translation engines, and writes text lines to stdout. &lt;code&gt;subtitle_overlay.py&lt;/code&gt; reads those lines and renders them as a transparent, always-on-top Qt overlay with typewriter reveal and smooth scrolling.&lt;/p&gt;</description></item></channel></rss>