Open source. Open possibilities.

NVIDIA NeMo Speech is an Apache-2.0 PyTorch framework for building, customizing and deploying speech AI models, covering automatic speech recognition, text-to-speech and speech LLMs, with pre-trained checkpoints and Docker/uv install paths.

An educational repository teaching supervised machine learning from first principles using Python, covering mathematical foundations and practical implementations.

FaceSwap is a deep learning-based tool for recognizing and swapping faces in images and videos. It provides extract, train, and convert stages with both CLI and GUI interfaces, supporting CUDA GPU acceleration.

Collection of simple PyTorch implementations of neural networks and deep learning papers with documented side-by-side explanations, covering transformers, GANs, diffusion models, RL, optimizers, and more.

Keras 3 is a multi-backend deep learning framework that allows users to build and train models using JAX, TensorFlow, PyTorch, or OpenVINO.

ONNX Runtime is a cross-platform accelerator for machine learning inference and training, supporting models from PyTorch, TensorFlow, and scikit-learn.

Sonnet is a neural network library by DeepMind built on TensorFlow 2. It provides simple, composable abstractions via the snt.Module concept for machine learning research, supporting custom modules, serialization, and distributed training.

A work-in-progress 2D game engine written in Java, designed for modularity and code-centric development without reliance on external libraries.

Unity ML-Agents Toolkit is an open-source framework that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning, with PyTorch-based implementations.

Video2X is a machine learning-based video super resolution and frame interpolation framework, rewritten in C/C++ for cross-platform Windows and Linux support.