NVIDIA releases open Nemotron 3.5 Transcribe, a 30B MoE speech model
Original title: NVIDIA Releases Nemotron 3.5 Transcribe: An Open 30B MoE Model for 40-Language Transcription with ~4B Active Parameters
The open model transcribes 40 languages while activating about 4 billion of its 30 billion parameters.
NVIDIA released Nemotron 3.5 Transcribe, described as an open speech large language model for transcription. It is a 30-billion-parameter mixture-of-experts model that keeps about 4 billion parameters active and covers 40 languages. The captured page body did not include further technical details.
Unconfirmed: The captured page body was cookie text, so only the title's claims are available.
- Nemotron 3.5 Transcribe is released as an open model.
- The model has 30 billion parameters in a mixture-of-experts design.
- About 4 billion parameters are active during inference.
- Transcription support covers 40 languages.
- Vendors
- NVIDIA
- AI models
- Nemotron 3.5 Transcribe
From the original article
14 min read at marktechpost.com
NVIDIA released Nemotron 3. 5 Transcribe, an open-weights speech LLM with 4. 3B active parameters.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.