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.
More from Infra
- Amazon Proposes Per-Request Validated Evidence Caching for Production RAG — _reachsumit · 2026-10-16
- LinkedIn's TransX report: sequence transduction for recsys, +6.02% CTR in A/B tests — _reachsumit · 2026-10-16
- llama.cpp PR boosts CPU inference speed with merged AVX2 tiled accumulators — jacek2023 · 2026-10-16
- Zero's next-gen IVM engine runs in a single DO, live-querying a 100GiB R2 database — threepointone · 2026-10-16
- Meme: driving to the chip factory in 2028 captures AI's compute anxiety — beffjezos · 2026-10-16
- One volunteer maintains the time zone file behind 4 billion phones — danbri · 2026-10-16