<div dir="ltr"><div dir="ltr"><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, Mar 4, 2024 at 10:49 PM Andrea paz via Cin <<a href="mailto:cin@lists.cinelerra-gg.org">cin@lists.cinelerra-gg.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">AVX2 and Machine Learning in the new release of Opus audio codec:<br>
<a href="https://opus-codec.org/" rel="noreferrer" target="_blank">https://opus-codec.org/</a></blockquote><div><br></div><div>"Deep learning also often gets associated with powerful GPUs, but
in Opus, we have optimized everything such that it easily runs on most
CPUs, including phones. We have been careful to avoid huge models (unlike LLMs with
their hundreds of billions of parameters!). In the end, most users should not notice the extra cost,
but people using older (5+ years) phones or microcontrollers might. For that reason, all new
ML-based features are disabled by default in Opus 1.5. They require both a compile-time
switch (for size reasons) and then a run-time switch (for CPU reasons)."</div><div><br></div><div><a href="https://opus-codec.org/demo/opus-1.5/">https://opus-codec.org/demo/opus-1.5/</a></div><div><br></div><div>Because I think we use it via libavcodec may be we should wait before relevant switch appear there ?<br></div><div><br></div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br>
-- <br>
Cin mailing list<br>
<a href="mailto:Cin@lists.cinelerra-gg.org" target="_blank">Cin@lists.cinelerra-gg.org</a><br>
<a href="https://lists.cinelerra-gg.org/mailman/listinfo/cin" rel="noreferrer" target="_blank">https://lists.cinelerra-gg.org/mailman/listinfo/cin</a><br>
</blockquote></div></div>