🚨 AI News | TestingCatalog· @testingcatalog · X·· 2 小时前同事件AI 评分72
AI 导读
NVIDIA 发布 Nemotron 3.5 Transcribe，这是一个开放权重的 30B MoE 模型，约 4B 激活参数。该模型支持 40 种语言转写、说话人归属、翻译、上下文提示和音频理解，并在 VoiceArena 的 14 系统说话人分离加 ASR 对比中排名第一。
同一件事，精选收录的是《Nvidia 发布开源语音模型 Nemotron 3.5 Transcribe，整合转写、翻译与说话人识别》
正文 · 原文
NVIDIA released Nemotron 3.5 Transcribe, a new open-weight, 30B MoE model with ~4B active parameters.
Nemotron 3.5 Transcribe can transcribe in 40 languages, perform speaker attribution, translate, handle contextual prompting, and understand audio.
It ranked first in VoiceArena’s 14-system diarization + ASR comparison.
Meet NVIDIA Nemotron 3.5 Transcribe 🎙️ An open-weight, promptable 30B MoE model with ~4B active parameters that brings transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding into one checkpoint. Watch it keep track of who said what when everyone’s talking at once. 1/ 🧵在 X 查看被引用的帖子
来源：🚨 AI News | TestingCatalog · x.com