hugpadhugpad

nvidia / NVIDIA-Nemotron-3.5-Transcribe-30B-A4B

Audio34B29.4K610Updated Oct 29, 2026
Hugging Face

Downloads

29.4K

Likes

610

Last updated

Oct 29, 2026

License

openmdw-1.1

Nemotron 3.5 Transcribe is an open-weight, offline speech and audio model for transcription in 40 languages, with support for recordings up to one hour and a 65,536-token context. Its hybrid mixture-of-experts architecture activates approximately 4.3B parameters, including the…

Tasks & library

  • automatic speech recognition
  • nemo

Tags

  • nemo
  • nemo_speechlm
  • text2text-generation
  • nvidia
  • pytorch
  • nemotron-3.5

Technical specifications

Parameters34B
Librarynemo
Languages40 languages
Base modelnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Licenseopenmdw-1.1