英伟达开源 Nemotron 3.5 Transcribe，整合转录、翻译与说话人识别
原标题：Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognition
AI 摘要
英伟达发布开源语音模型 Nemotron 3.5 Transcribe，该模型支持文本指令，将转录、翻译和说话人识别整合到单一模型中，覆盖多达 40 种语言。模型总参数 300 亿，但每步仅激活约 40 亿，可在单张 GPU 上运行，并在多个基准测试中名列前茅。英伟达同时发布包含 84.4 万小时音频的 Granary v2 数据集及微调工具，便于开发者适配医疗等专业领域。
正文节选
Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognition Key Points - Nvidia has released Nemotron 3.5 Transcribe, an open speech model that follows text commands and combines transcription, translation, and speaker recognition for up to 40 languages. - The model has 30 billion parameters, but only 4 billion are active per step, so it runs on a single GPU. It ranks near the top of benchmarks for accuracy and speaker attribution. - Nvidia is also releasin