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
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
I wonder if Apple will acquire them?
https://www.macrumors.com/2026/05/28/apple-to-make-on-device...
pretty speedy for local compute!