E2e music remastering system - End-to-end Music Remastering System Using Self-supervised and Adversarial Training

Last update: Dec 15, 2022

Overview

End-to-end Music Remastering System

This repository includes source code and pre-trained models of the work End-to-end Music Remastering System Using Self-supervised and Adversarial Training by Junghyun Koo, Seungryeol Paik, and Kyogu Lee.

We provide inference code of the proposed system, which targets to alter the mastering style of a song to desired reference track.

Pre-trained Models

Model	Number of Epochs Trained	Details
Music Effects Encoder	1000	Trained with MTG-Jamendo Dataset
Mastering Cloner	1000	Trained with the above pre-trained Music Effects Encoder and Projection Discriminator

Inference

To run the inference code,

Download pre-trained models above and place them under the folder named 'model_checkpoints' (default)
Prepare input and reference tracks under the folder named 'inference_samples' (default).
Target files should be organized as follow:

    "path_to_data_directory"/"song_name_#1"/input.wav
    "path_to_data_directory"/"song_name_#1"/reference.wav
    ...
    "path_to_data_directory"/"song_name_#n"/input.wav
    "path_to_data_directory"/"song_name_#n"/reference.wav

Run 'inference.py'

python inference.py \
    --ckpt_dir "path_to_checkpoint_directory" \
    --data_dir_test "path_to_directory_containing_inference_samples"

Outputs will be stored under the folder 'inference_samples' (default)

Note: The system accepts WAV files of stereo-channeled, 44.1kHZ, and 16-bit rate. Target files shold be named "input.wav" and "reference.wav".

Configurations of each sub-networks

A detailed configuration of each sub-networks can also be found at

Self_Supervised_Music_Remastering_System/configs.yaml

E2e music remastering system - End-to-end Music Remastering System Using Self-supervised and Adversarial Training

Related tags

Overview

End-to-end Music Remastering System

Pre-trained Models

Inference

Configurations of each sub-networks

Owner

Junghyun (Tony) Koo

Implementation of a Transformer, but completely in Triton

Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks

Official implementation of ETH-XGaze dataset baseline

This is the research repository for Vid2Doppler: Synthesizing Doppler Radar Data from Videos for Training Privacy-Preserving Activity Recognition.

Benchmarks for the Optimal Power Flow Problem

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Implementation of "GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings" in PyTorch

A script that trains a model to recognize handwritten digits using the MNIST data set.

Official Repo of my work for SREC Nandyal Machine Learning Bootcamp

Pytorch library for end-to-end transformer models training and serving

A two-stage U-Net for high-fidelity denoising of historical recordings

OpenMMLab Detection Toolbox and Benchmark

Leaderboard and Visualization for RLCard

Zeyuan Chen, Yangchao Wang, Yang Yang and Dong Liu.

Unsupervised Feature Loss (UFLoss) for High Fidelity Deep learning (DL)-based reconstruction

An intuitive library to extract features from time series

PyTorch implementation of the paper Dynamic Token Normalization Improves Vision Transfromers.

Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

The Curious Layperson: Fine-Grained Image Recognition without Expert Labels (BMVC 2021)

Pyramid Scene Parsing Network, CVPR2017.