ruohoruotsi

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

manim

Animation engine for explanatory math videos

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

s4

Structured state space sequence models

ffmpeg-normalize

Audio Normalization for Python/ffmpeg

open-unmix-pytorch

Open-Unmix - Music Source Separation for PyTorch

STIT

audino

Open source audio annotation tool for humans

libri-light

dataset for lightly supervised training using the librivox audio book recordings. https://librivox.org/.

css10

CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages

torchvggish

Pytorch port of Google Research's VGGish model used for extracting audio features.

LakhNES

Generate 8-bit chiptunes with deep learning

da-rnn

Dual-Stage Attention-Based Recurrent Neural Net for Time Series Prediction

BeatNet

BeatNet is state-of-the-art (Real-Time) and Offline joint music beat, downbeat, tempo, and meter tracking system using CRNN and particle filtering. (ISMIR 2021's paper implementation).

soundata

Python library for downloading, loading & working with sound datasets

torchaudio-augmentations

Audio transformations library for PyTorch

audacitorch

PyTorch wrappers for using your model in audacity!

ml-audio-start

Suggestions for those interested in developing audio applications of machine learning

torch-pitch-shift

Pitch-shift audio clips quickly with PyTorch (CUDA supported)! Additional utilities for searching efficient transformations are included.

MetaMIDIDataset

keras-layer-normalization

Layer normalization implemented in Keras

cv-sentence-extractor

Scraping Wikipedia for fair use sentences

e2e_music_remastering_system

source code of "End-to-end Music Remastering System Using Self-supervised and Adversarial Training"

ood_audio

An audio classification system for learning with out-of-distribution data

pitchclass_mctc

Pytorch project accompanying the paper "Training Deep Pitch-Class Representations With a Multi-Label CTC Loss", ISMIR 2021.

MINGUS

MINGUS is a transformer neural network that generates symbolic music

bible2speechDB

Scripts to create speech corpora from open.bible

menyo-20k_MT

GMM_MusicVAE

Demos for GMM and MusicVAE work

LakhNES

Generate 8-bit chiptunes with deep learning