Peaked at #2 Now #3
NVIDIA Launches Nemotron Transcribe Model
NVIDIA launches open-weight Nemotron 3.5 Transcribe, a 30B MoE with ~4B active params supporting 40-language transcription and speaker attribution.
Key points
- NVIDIA released Nemotron 3.5 Transcribe, an open-weight, promptable 30B MoE model with ~4B active parameters that supports transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding in one checkpoint.
- Nemotron 3.5 Transcribe ranks #1 among open-weight models on the Hugging Face Open ASR English leaderboard with a 5.33% average word error rate, according to the original poster.
- NVIDIA also released MotionBricks, which generates character motion at a reported 15,000 frames per second with just 2ms latency on an RTX 5090, trained on 350,000+ motion clips.
Key points and the reaction summary are written by AI from the posts on this page. Check the original post. How we use AI
Original post
Meet NVIDIA Nemotron 3.5 Transcribe 🎙️
An open-weight, promptable 30B MoE model with ~4B active parameters that brings transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding into one checkpoint.
Watch it keep track of who said what when everyone’s talking at once.
1/ 🧵
Top replies on X
Sign in to see 2 top replies from X
From @NVIDIAAI, @baseten and others. Spam removed, with English and Chinese translations.
Discussion 0
Sign up Sign in to join the discussion
No comments yet. Start the conversation.