Nvidia 发布开源转写模型 Nemotron 3.5 Transcribe
Voice AI in vogue: Nvidia releases new open transcription model
Nvidia 发布免费开源权重模型 Nemotron 3.5 Transcribe，可转写最多 40 种语言的音频，并同步推出开源语音数据集 Granary 第 2 版。该模型支持 31 种语言与英语互译、处理最长一小时的录音、区分最多 8 位说话人，Nvidia 称其在 Hugging Face Open ASR Leaderboard 等基准上优于竞品。模型为 300 亿参数，可运行在 Jetson AGX Thor、DGX Spark 及 Blackwell 数据中心芯片上，但只支持录音音频，不支持直播流。
推荐理由
AI 评分 69
原文列出 Nemotron 3.5 Transcribe 的语言覆盖、说话人分离和单芯片运行条件，便于判断它在转写场景的适用范围。
主题
正文
Nvidia on Wednesday released Nemotron 3.5 Transcribe , a free, open-weight model that transcribes audio in up to 40 languages. It also released version 2 of Granary, its open source speech dataset.
Nvidia boasts that Nemotron 3.5 can translate 31 languages to and from English, handle recordings up to an hour long, and tell up to eight speakers apart. It claims to beat rivals on benchmarks, including Hugging Face’s Open ASR Leaderboard .
These tools target developers building apps for business meetings and medical transcription, two of AI’s most established footholds in the workplace. Nvidia says developers can use the model, the updated Granary dataset, and tools like its NeMo Speech model to customize apps to recognize an industry’s jargon in each language. One drawback: Transcribe works with recorded audio, not livestreams.
Still, the company promises Transcribe, at 30 billion parameters, can run on a single chip, from the Jetson AGX Thor robotics controller and DGX Spark chip powering new laptops , to Blackwell datacenter chips. It joins Nvidia’s open-weight voice models, including the super small yet powerful Parakeet (1.1 billion parameters).
Nvidia’s latest voice entry comes during a busy period of AI voice releases: Mistral shipped Voxtral 3 earlier this month; ElevenLabs launched Realtime for instant speech in voice agents; and Salesforce released Launa-Omni, its voice model.