Nvidia 开源 1 亿参数说话人分离模型 Nemotron 3 Diarization
Nvidia drops a free 100M-parameter model that identifies up to eight speakers in real time
精选理由
Nvidia 免费放了个 1 亿参数的小模型，能实时分辨最多 8 个说话人，做会议转写或字幕的可以试试。
Nvidia 发布 Nemotron 3 Diarization，参数量约 1 亿，可实时判断一段对话中正在说话的人是谁。模型最多支持同时识别 8 个说话人，并免费开放使用。这类说话人分离任务常用于会议转写、字幕生成等场景。
原文 · Decoder
Nvidia drops a free 100M-parameter model that identifies up to eight speakers in real time
Nvidia released Nemotron 3 Diarization, an AI model that identifies which speaker is talking at any given moment in a conversation. The article Nvidia drops a free 100M-parameter model that identifies up to eight speakers in real time appeared first on The Decoder .
- Genspark09-25 17:33原文
