nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
Automatic Speech Recognition • 34B • Updated • 4.28k • • 442
Nemotron 3.5 Transcribe
Open-weight offline ASR model supporting 40 languages, 1-hr audio, and 64k context. Hybrid MoE (~4.3B active). Available in BF16, FP8, and NVFP4.
-
-
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-FP8
Automatic Speech Recognition • 34B • Updated • 161 • 1 -
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4
Automatic Speech Recognition • 19B • Updated • 202 • 13 -
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-DFlash2
0.6B • Updated • 90 • 10 -
Nemotron Transcribe
🏃18NVIDIA Nemotron Transcribe Demo
-
nvidia/Granary-v2
Updated • 1.07k • 29 -
nvidia/Granary-HiFi
Viewer • Updated • 92.1M • 355 • 6