NVIDIA 发布 Nemotron 3.5 Transcribe 与 Granary v2
原标题：NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt
AI 摘要
NVIDIA 发布开源权重模型 Nemotron 3.5 Transcribe，将多语言转写、说话人分离、翻译和音频问答整合到单一检查点，支持 40 种语言转写、31 种语言与英语互译、13 种语言说话人标注，可处理长达一小时录音并标注最多 8 位说话人。该模型在 Hugging Face Open ASR 英文榜开源权重模型中排名第一（平均 WER 5.33%），在 Artificial Analysis 榜单以约 4B 激活参数并列开源第一。NVIDIA 同时开源 Granary v2 数据管线与微调方案，医疗场景微调后词错误率相对最佳提示词降低 45.8%。
正文节选
NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt One open model for multilingual transcription, speaker attribution, translation, and audio Q&A, with top leaderboard results, plus the open Granary v2 data pipeline and fine-tuning recipes to adapt it. A transcript can capture every spoken word and still leave users or applications wondering who said what, how to translate it, or how to format domain-specific jargon. Multilingual calls,