NVIDIA's open-weight speech LLM: transcription in 40 languages, speakers, word timestamps, context terms and translation in 1 model. Compared with Whisper large-v3 on my Mac Studio M1 Ultra.

NVIDIA's open-weight 100M-parameter model that tells who spoke when, for up to 8 speakers, live or recorded. Ranked first on VoiceArena's diarization benchmark at launch.