Tensors and Dynamic neural networks in Python with strong GPU acceleration

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

PyTorch tutorials.

Boto3, an AWS SDK for Python

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

Defines a dynamic module type that lets you create objects in the dynamic module on demand

Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.

Google Research

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

kapre: Keras Audio Preprocessors

ezkl is an engine for doing inference for deep learning models and other computational graphs in a zk-snark (ZKML). Use it from Python, Javascript, or the command line.

Keras implementation of Legendre Memory Units

🇸Superpowered Audio, Networking and Cryptographics SDKs. High performance and cross platform on Android, iOS, macOS, tvOS, Linux, Windows and modern web browsers.

JAX-based neural network library

Table with operator formulas and mappings at a glance, as much ML documentation is missing details

The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

TFHE: Fast Fully Homomorphic Encryption Library over the Torus

Read, write and manipulate GP3, GP4 and GP5 files.

A complete computer science study plan to become a software engineer.

An Open Source Machine Learning Framework for Everyone

Music Structure Analysis Framework

Magenta: Music and Art Generation with Machine Intelligence

Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

Converts an ONNX ML model protobuf from/to text, or tensor from/to text/CSV/raw data. (Windows command line tool)

The purpose of Raster Fairy is to transform any kind of 2D point cloud into a regular raster whilst trying to preserve the neighborhood relations that were present in the original cloud. A typical …

an implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch

Differentiable Vector Graphics Rasterization

Deep learning driven jazz generation using Keras & Theano!