NVIDIA NeMo 3.0 Refactors Architecture, Focuses Entirely on Speech Models

kuchaev · x · 2026-08-07

NVIDIA has officially split its NeMo research library, renaming the original repository to NVIDIA-NeMo/Speech and upgrading it to version 3.0 with a dedicated focus on ASR, TTS, and SpeechLLM technologies.

The new release heavily addresses technical debt by removing almost 1 million deprecated lines of code, cutting over 100 dependencies, and migrating to uv for a streamlined installation. It also introduces new features, including integration with NeMo Automodel for distributed SpeechLLM training and the addition of MagpieTTS.

Original post →

More from Infra

Infra channel →