NVIDIA-NeMo/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)

73
/ 100
Verified

This project helps AI researchers and PyTorch developers build, customize, and deploy advanced speech and multimodal AI models. It takes in various speech and text data, allowing users to create custom automatic speech recognition (ASR), text-to-speech (TTS), and speech-enabled large language models (LLMs). The primary users are machine learning engineers and researchers focused on developing sophisticated conversational AI applications.

16,894 stars. Actively maintained with 51 commits in the last 30 days.

Use this if you are an AI researcher or developer working with PyTorch and need a robust framework to build, customize, and deploy scalable speech and multimodal generative AI models.

Not ideal if you are looking for a pre-built, out-of-the-box solution without needing to customize or train models, or if you are not comfortable with deep learning development frameworks like PyTorch.

Speech AI Natural Language Processing Conversational AI Generative AI Machine Learning Development
No Package No Dependents
Maintenance 22 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

16,894

Forks

3,365

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

51

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/NVIDIA-NeMo/NeMo"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.