Nvidia releases open multi-task speech model and dataset
What happened
On October 28, TechCrunch reported that Nvidia released Nemotron 3.5 Transcribe, a free open-weight speech model that transcribes audio in up to 40 languages, alongside version 2 of its open speech dataset Granary. A Hacker News front-page report added that one checkpoint bundles transcription, speaker attribution, translation and audio question answering: 40 languages transcribed, 31 languages translated to and from English, and speaker attribution in 13 languages. The Decoder later reported the tasks are invoked through text instructions. No benchmark results, language list or dataset size were disclosed.
Written by AI from the coverage · updated 1 hour ago
Coverage
Follow the reports to see the story from different sides.
- The DecoderPickNvidia releases open speech model Nemotron 3.5 Transcribe for transcription, translation and speaker ID
Nvidia released Nemotron 3.5 Transcribe, an open speech model that handles transcription, translation, speaker recognition and audio question answering through text instructions. Fine-tuning it on mostly synthetic speech data for medical transcription cut the error rate from 23.8% to 11.8%, and Nvidia also documented the loss in general English accuracy that came with it.
- Hacker News front pageNvidia Nemotron 3.5 Transcribe: open ASR for 40 languages
NVIDIA 发布开放权重模型 Nemotron 3.5 Transcribe，在一个 checkpoint 中整合语音转写、说话人归属、翻译和音频问答，支持 40 种语言转写、31 种语言与英语互译及 13 种语言的说话人归属。
- TechCrunch · AIVoice AI in vogue: Nvidia releases new open transcription model
英伟达发布免费开放权重模型 Nemotron 3.5 Transcribe，支持最多 40 种语言的音频转录，并推出开源语音数据集 Granary 第 2 版。
Heat over time
Heat now 28·Comparable peak 29（Oct 29 01:00）·Comparable change over 24 hours –
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.