https://www.drmhse.com/tags/apple-silicon/Recent content in Apple-Silicon on DRM HSEHugoenSun, 26 Jul 2026 19:00:04 +0300https://www.drmhse.com/posts/running-funaudio-on-mac-mlx-pytorch/Sat, 25 Jul 2026 17:53:14 +0300https://www.drmhse.com/posts/running-funaudio-on-mac-mlx-pytorch/<p>I have been using a local <a href="https://github.com/FunAudioLLM/CosyVoice"target="_blank" rel="noopener noreferrer" class="external-link">CosyVoice3<svg class="inline-block w-3 h-3 ml-0.5 align-baseline" fill="none" stroke="currentColor" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg" aria-hidden="true"> <path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M10 6H6a2 2 0 00-2 2v10a2 2 0 002 2h10a2 2 0 002-2v-4M14 4h6m0 0v6m0-6L10 14"></path> </svg> </a> service to narrate audiobooks—a few thousand clips of production output, one segment at a time, over a couple of weeks. It worked. It was also slower than real time, which I had accepted as the price of running a 0.5B TTS model on a laptop.</p>