Speech
2 updates on Speech.
Nvidia releases Nemotron-3-Diarization, a 100M speaker model with 0.32 second latency
Nemotron-3-Diarization labels up to eight speakers in streaming or offline audio and ranks first on Voice Arena’s Diarization-Bench v1 with 14.7% DER.
RikkaHub Agent test: Android phone agent compiles whisper.cpp on its own
XDA runs RikkaHub Agent on an Oppo Find N5 against a self-hosted Qwen 3.6 27B. The agent installed dependencies and built whisper.cpp in Termux in seven minutes.