NVIDIA 发布开源语音模型 Nemotron 3.5 Transcribe
NVIDIA 出了个开源语音模型，开会录音能转文字、分清谁在说话，还能翻译和直接问录音内容，30B 参数本地 GPU 就能跑。
NVIDIA 发布开源语音模型 Nemotron 3.5 Transcribe，支持 40 种语言转录和英语与 31 种语言互译。模型可区分最多 8 个说话人并打标签，处理最长一小时的录音。参数量约 30B（每 token 激活约 4B），可在本地 NVIDIA GPU 上运行。官方称其在 Hugging Face 英语 Open ASR 榜单开源模型中排名第一，并在 VoiceArena 14 系统说话人归属转录测试中领先。还支持音频问答，可指定人名和技术术语引导转录。
NVIDIA is releasing an open speech model that can transcribe a meeting, label who said what, translate it and answer questions about the recording:
Nemotron 3.5 Transcribe supports: - Transcription in 40 languages - Translation between English and 31 languages - Up to eight speakers, with speaker labels in 13 languages - Recordings up to an hour long
You can give it names and technical terms to guide the transcript, or ask questions about the audio. Audio Q&A is trained in English.
It has roughly 30B parameters, with about 4B active per token, and can run on your own NVIDIA GPU.
According to NVIDIA's launch materials, it ranks first among open-weight models on Hugging Face's English Open ASR leaderboard and leads VoiceArena's 14-system test of transcription with speaker attribution.
Built for recorded audio. Live streaming uses a separate model.
Super cool to see!
Model: https://t.co/jEe0LRZoqg Demo: https://t.co/xIr5mf0PCV Blog: https://t.co/mQk95Waudq
