NVIDIA Nemotron 3 Diarization is now available on ModelScope—adding live speaker attribution to existing ASR workflows without replacing the transcription model. 🎙️ 🤖 modelscope.ai/models/nv-comm… 👥 Processes streaming audio and returns speaker labels and timestamps for up to eight speaker slots in a single conversation. ⚡ Its end-to-end streaming architecture avoids separately combining voice activity detection, speaker embeddings, clustering, and post-processing. 🧠 The 99.2M-parameter model uses a 31-layer Transformer encoder with RoPE and builds on NVIDIA’s Streaming Sortformer architecture. 🔌 Pair it with Nemotron ASR, Parakeet, Canary, Whisper, or another ASR system to create speaker-attributed transcripts. 🏢 Designed for meetings, contact centers, clinical conversations, live captioning, media analysis, and multi-party voice agents. 🖥️ Supports NVIDIA Ampere, Hopper, and Blackwell GPUs, with inference through NeMo Speech C++.

Big update: @WaveFormsAI was acquired by @Meta. Today at #MetaConnect, you’ll see a little of what we’ve all been building. ✨🤖

Even in chaotic moments, people can be kind

Data is more important than ever

Speech‑to‑speech generation eliminates the need for separate (TTS) text‑normalization and prosody modeling, both of which are notoriously hard.

Free will, so often overlooked, becomes priceless only when it slips away.