🎛 🔊 A Python library for audio.

Deezer source separation library including pretrained models.

Code for the paper Hybrid Spectrogram and Waveform Source Separation

This is the repo for my experiments with StyleGAN2. There are many like it, but this one is mine. Contains code for the paper Audio-reactive Latent Interpolations with StyleGAN.

Audio generation using diffusion models, in PyTorch.

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

Steerable discovery of neural audio effects

Fast Infinite Waveform Music Generation

Collection of audio-focused loss functions in PyTorch

Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

Guitar plugin made with JUCE that uses neural networks to emulate a tube amplifier.

A simple library and set of tools for parsing, modifying, and composing SRT files.

Robust Speech Recognition via Large-Scale Weak Supervision

A PyTorch-based Speech Toolkit

Official implementation of "Learning Music Audio Representations Via Weak Language Supervision" (ICASSP 2022)

Official implementation of "Contrastive Audio-Language Learning for Music" (ISMIR 2022)

Source code for "MusCaps: Generating Captions for Music Audio" (IJCNN 2021)

Guitar plugin made with JUCE that uses neural network models to emulate real world hardware.

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Tools to train a generative model on arbitrary audio samples

Audio Dataset for training CLAP and other models

Trainer for audio-diffusion-pytorch

A collection of useful audio datasets and transforms for PyTorch.

DeepAFx-ST - Style transfer of audio effects with differentiable signal processing. Please see https://csteinmetz1.github.io/DeepAFx-ST/

A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.

NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling @ INTERSPEECH 2021

Muzic: Music Understanding and Generation with Artificial Intelligence