Event ·Multi-source

NVIDIA 发布 Nemotron 3.5 Transcribe 开源语音转写模型

NVIDIA 推出开源语音转写模型 Nemotron 3.5 Transcribe,总参数量 30B、激活参数仅 4B。该模型在 AA-WER Index 上取得 2.8% 的错误率,与 Mistral 的 Voxtral Small 并列开源模型第一。在语音智能体对话数据集 AA-AgentTalk 上,它以 1.8% 的错误率领先 Voxtral Small 的 2.3%。相比 Voxtral Small 的 24B 激活参数,它用少 6 倍的激活参数达到同等准确率,而同规模开源模型的错误率普遍在 4% 左右。

Current read

NVIDIA 的开源语音转写模型用 4B 激活参数做到 2.8% 错误率,比 Mistral Voxtral Small 少 6 倍参数还打平,做语音智能体的可以看看。

11 sources61° AI heatLast updated 2026/10/28 15:05:14

Evidence

11 sources
Primary sourceArtificial Analysis
View source
Related source 3Hugging Face: Blog
View source
Related source 4techcrunch
View source
Related source 5rohanpaul_ai
View source
Related source 6TestingCatalog
View source
Related source 7CoreWeave
View source
Related source 8Gorden Sun
View source
Related source 9arXiv cs.AI
View source
Related source 10Tech in Asia
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

NVIDIA Nemotron 3.5 Transcribe ties for #1 open-weight STT · 事件专题 | AITOP