英伟达发布 Nemotron 3.5 Transcribe
英伟达发布开放权重、可通过提示控制的 Nemotron 3.5 Transcribe,将录音转录、翻译、说话人区分和音频问答整合到同一模型,并同步推出 Granary v2 数据整理管线和微调资源。报道显示,该模型支持40种语言、其中31种可与英语互译、最多标注8名说话人,现已登陆 Hugging Face 和 ModelScope,但不支持实时流式转录。基准成绩主要由 NVIDIA 公布,而各报道对参数规模、音频长度及部分基准数据存在差异。
该发布让开发者能够用开放权重模型统一处理多项录音任务,并可借助 Granary v2 针对专业术语和转录格式进行微调。
Nvidia Corp. today released a leaderboard-winning open artificial intelligence model for multilingual audio transcription and translation, along with an open data pipeline for fine-tuning Nemotron 3.5 Transcribe.
Traditional transcription AI models follow a workflow that detects speech, transcribes it, identifies and labels different speakers, then answers questions about the transcription. Transcribe does all of this in a single model pass and is capable of digesting and answering questions about 100 hours of audio, in 40 languages and can label up to eight speakers.
It’s an open-weight, 30-billion parameter mixture-of-experts model with 4 billion active parameters. That means it can fit on reasonably small hardware, though more powerful hardware lets it transcribe faster.
For its size, Transcribe punches way above its weight and it can run anywhere from the edge to the data center depending on compression. The model runs on a single Nvidia graphics processing unit, from a Jetson AGX Thor, an edge computer robot brain, or DGX Spark, a desktop AI supercomputer, all the way to a Blackwell data-center GPU. Nvidia said a Blackwell Server Edition GPU with NVFP4 precision and one-quarter model compression processes 100 hours of audio in under three minutes.
#NVIDIA#Nemotron 3.5 Transcribe#Granary v2#NeMo Speech#NeMo Curator