🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

The agent engineering platform.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

scikit-learn: machine learning in Python

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Open standard for machine learning interoperability

Impacket is a collection of Python classes for working with network protocols.

music library manager and MusicBrainz tagger

StyleGAN2 - Official TensorFlow Implementation

Hydra is a framework for elegantly configuring complex applications

Code for the paper "Jukebox: A Generative Model for Music"

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

Muzic: Music Understanding and Generation with Artificial Intelligence

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

DDSP: Differentiable Digital Signal Processing

🎚️ Open Source Audio Matching and Mastering

This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.

Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

Python audio and music signal processing library

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)

Audio processing by using pytorch 1D convolution network

Realtime audio analysis in Python to extract audio features from streaming audio and send them over OSC to any client app.

An All-MLP solution for Vision, from Google AI