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
- AI token black market: $100 Claude API credits for $8, some losing $10M/month — michellechen · 2026-08-08
- Qualcomm Pushes Native On-Device AI Agents, Challenging NPU-Centric Narratives — ryanshrout · 2026-08-08
- GPT-5.6 Price Cut Triggers Jevons Paradox: Token Consumption Jumps 10x — rohanpaul_ai · 2026-08-08
- Altman Congratulates Oklo as Nuclear Reactor Achieves Criticality in Under a Year — sama · 2026-08-08
- Visualizing LLM API Price Volatility: An Open-Source Tool to Justify Local Compute Budgets — olddoglearnsnewtrick · 2026-08-08
- 10kAmp AI Chips Face Severe Power Delivery and Cooling Challenges — jwt0625 · 2026-08-08