Event ·Multi-source

NVIDIA 开源 Nemotron 3 Diarization 说话人分离模型

NVIDIA 发布并开源 Nemotron 3 Diarization 模型,可在实时对话中追踪不同说话人,采用商业友好许可证。据 Hugging Face 员工 Andi Marafioti 测试,模型在 1 秒语音片段下表现良好,可用于语音智能体。测试中还配合 Pollen Robotics 的 Reachy Mini 机器人和 DGX Spark,实现识别新声音、询问并记住对方姓名。模型发布即支持 Transformers 集成。

Current read

NVIDIA 开源了个说话人追踪模型,1秒语音就能分清谁在说话,还能让 Reachy Mini 机器人认人记名字,商用许可也友好。

11 sources76° AI heatLast updated 2026/9/23 15:23:13

Evidence

11 sources
Related source 2Thomas Wolf
View source
Related source 3Hugging Face: Blog
View source
Related source 4rohanpaul_ai
View source
Related source 5Clement Delangue
View source
Related source 6arXiv cs.LG
View source
Related source 7Rest of World
View source
Related source 9shao__meng
View source
Related source 10LangChain
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.