NVIDIA NeMo
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
NVIDIA NeMo scores 7.8/10 (Strong) in Voice & Realtime.
Language Python License Apache-2.0 Stars 17.7k★ Type heavyweight Self-host Yes Repo NVIDIA/NeMo Homepage https://github.com/NVIDIA/NeMo
Quality
Strong 7.8
Adoption 56
Activity 80
Maturity 100
Community 64
Capability 94
Show the math
Overall 7.8/10
value = 7.8/10
score = value
Adoption 6.1/10
value = 56.2/100
score = 1 + 9 * value / 100
Activity 8.2/10
value = 80.2/100
score = 1 + 9 * value / 100
Maturity 10/10
value = 100/100
score = 1 + 9 * value / 100
Community 6.8/10
value = 64.3/100
score = 1 + 9 * value / 100
Capability 9.5/10
value = 94/100
score = 1 + 9 * value / 100
Key metrics
17.7k★ GitHub stars
145/90d Recent commits
30 devs/90d Recent contributors
6.05% WER WER, HF Open-ASR Leaderboard average (Parakeet TDT 0.6B v2, NeMo) NVIDIA NeMo's Parakeet TDT 0.6B v2 reports an industry-best 6.05% average WER on the Hugging Face Open-ASR Leaderboard. Reported as 100-WER. Source: NVIDIA developer blog (https://developer.nvidia.com/blog/nvidia-speech-ai-models-deliver-industry-leading-accuracy-and-performance/), corroborated by AWS ML blog.
6.9y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
- Heavyweight
Heavyweight
Resource-heavy to run (GPU, large memory, or multi-service stack).
asr framework parakeet streaming nvidia