Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

A GUI frontend for @werman's Pulse Audio real-time noise suppression plugin

IDA Pro plugin which improves work with HexRays decompiler and helps in process of reconstruction structures and classes

CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.

Python Filter Design Analysis Tool

PyTorch's implementation of the code2seq model.

Generative timbre spaces by perceptually regularizing variational auto-encoders

Moved to gitlab: https://gitlab.com/Moini/inkscape-extensions-multi-bool/ (A set of inkscape extensions to apply a boolean operation on multiple shapes at once)

Allen & Heath dLive OSC-like gateway for qLab via AH-NET