NVIDIA 发布开源语音模型 Nemotron 3.5 Transcribe
NVIDIA 发布开源语音模型 Nemotron 3.5 Transcribe，可转写会议录音、标注说话人、翻译并回答音频问题。模型支持 40 种语言转写、英语与 31 种语言互译、最多 8 位说话人及最长 1 小时录音，说话人标签支持 13 种语言；可输入姓名和技术术语引导转写，音频问答以英语训练。
模型支持多语言转写、说话人标注、翻译和音频问答，参数规模与运行方式便于评估本地部署可行性。
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: huggingface.co/nvidia/NVIDIA…
Demo: huggingface.co/spaces/nvidia…
Blog: huggingface.co/blog/nvidia/n…
来源：kimmonismus · x.com