Interesting that you expanded the LFM2.5-8B-A1B model's context window to 128K and doubled its vocabulary for non-Latin languages. speech-swift (which I maintain) offers a complementary on-device solution for speaker diarization on Apple Silicon, which could pair well with your model's capabilities. https://soniqo.audio/guides/diarize
3 comments
[ 0.98 ms ] story [ 781 ms ] threadhttps://www.macrumors.com/2026/05/28/apple-to-make-on-device...