算力商业
x.com ·
@NVIDIAAI
NVIDIA 发布 Nemotron 3 Diarization：100M 参数、支持 8 人重叠语音的说话人分离模型
NVIDIA AI 官方账号感谢用户下载 Nemotron 3 Diarization，并称该模型在 Hugging Face 上受到关注。该模型用于说话人分离（diarization），可追踪谁在何时说话，即使声音重叠也能处理，最多支持 8 位说话人，参数量为 100M，已在 Hugging Face 上线。推文附有答疑视频，但未提供基准测试或效果验证数据。
AI推荐理由 NVIDIA 官方账号发布的 Nemotron 3 Diarization 模型信息：100M 参数、支持最多 8 人说话人分离、可处理语音重叠，已在 Hugging Face 上线。属于官方产品发布，事实明确、信息密度尚可；但本条推文主要是致谢与答疑视频，正文未给出评测数据、基准或技术细节，互动量仅作传播信号，不能证明实际效果。
62
浏览 4,018
点赞 27
评论 2
转发 1
正文
Huge thank you to everyone who downloaded Nemotron 3 Diarization and helped it trend on [@huggingface](https://x.com/huggingface)! And we appreciate all the comments.
[@sabbassi\_11](https://x.com/sabbassi_11) answered a few of your questions:
[Your browser does not support the video tag.](https://video.twimg.com/amplify_video/2106179749425102848/vid/avc1/1080x1920/ieWrUMz5hqx1bscA.mp4?tag=29)
[🔗 View on Twitter](https://x.com/NVIDIAAI/status/2106179861811445771/video/1)
NVIDIA AI@NVIDIAAI
When several people talk at once, a transcript can get messy fast.
Our new Nemotron 3 Diarization model tracks who spoke when, even when voices overlap. It handles up to eight speakers, has 100M parameters, and is now available on [@huggingface](https://x.com/huggingface) 🤗
[Your browser does not support the video tag.](https://video.twimg.com/amplify_video/2102769845846896640/vid/avc1/1910x790/_iVyj0b4hIjDiJiS.mp4?tag=29)
[🔗 View on Twitter](https://x.com/NVIDIAAI/status/2102775666366435450/video/1)
[🔗 View Quoted Tweet](https://x.com/NVIDIAAI/status/2102775666366435450)