Code for unmixing audio signals in four different stems "drums, bass, vocals, others". The code is adapted from "Jukebox: A Generative Model for Music"

Last update: Dec 29, 2022

Related tags

Deep Learning unmix

Overview

Status: Archive (code is provided as-is, no updates expected)

Disclaimer

This code is a based on "Jukebox: A Generative Model for Music" Paper

We adjusted it for our application: Demixing an audio signal into four different stems: drums, basss, vocals, other.

Unmix

Install

Install the conda package manager from https://docs.conda.io/en/latest/miniconda.html

# Required: Sampling
conda create --name unmix python=3.7.5
conda activate unmix
conda install mpi4py=3.0.3 # if this fails, try: pip install mpi4py==3.0.3
conda install pytorch=1.4 torchvision=0.5 cudatoolkit=10.0 -c pytorch
git clone https://github.com/wzaiealmri/unmix.git
cd unmix
pip install -r requirements.txt
pip install -e .

# Required: Training
conda install av=7.0.01 -c conda-forge
pip install ./tensorboardX

# Optional: Apex for faster training with fused_adam
conda install pytorch=1.1 torchvision=0.3 cudatoolkit=10.0 -c pytorch
pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./apex

Training

Stage 1: VQVAE

To train the vqvae, run

mpiexec -n {ngpus} python unmix/train.py --hps=vqvae --name=vqvae_drums_b4 --sr=44100 --sample_length=393216 --bs=4 --audio_files_dir="Put the path to the specific stem audio folder" --labels=False --train --aug_shift --aug_blend

Here, {audio_files_dir} is the directory in which you can put the audio files for your stem , and {ngpus} is number of GPU's you want to use to train. The above trains a one-level VQ-VAE with downs_t = (3), and strides_t = (2) meaning we downsample the audio by 2**3 = 8 to get the first level of codes.
Checkpoints are stored in the logs folder. You can monitor the training by running Tensorboard

tensorboard --logdir logs

Stage 2: Encoder

Train encoder

Once the VQ-VAE is trained, we can restore it from its saved checkpoint and train encoder on the learnt codes. To train the encoder, we can run

mpiexec -n {ngpus} python unmix_encoder/train.py --hps=vqvae --name=encoder_drums__b4 --sr=44100 --sample_length=393216 --bs=4 --audio_files_dir="path to the mix dataset" --labels=False --train --aug_shift --aug_blend --encoder=True --channel=_1 --restore_vqvae="path to the specific checkpoint of the vq-vae"

License (Jukebox OpenAI)

Noncommercial Use License

It covers both released code and weights.

Code for unmixing audio signals in four different stems "drums, bass, vocals, others". The code is adapted from "Jukebox: A Generative Model for Music"

Related tags

Overview

Disclaimer

Unmix

Install

Training

Stage 1: VQVAE

Stage 2: Encoder

Train encoder

License (Jukebox OpenAI)

Owner

Wadhah Zai El Amri

PyTorch code for the "Deep Neural Networks with Box Convolutions" paper

Dataset and codebase for NeurIPS 2021 paper: Exploring Forensic Dental Identification with Deep Learning

Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.

This package implements the algorithms introduced in Smucler, Sapienza, and Rotnitzky (2020) to compute optimal adjustment sets in causal graphical models.

Automatic meme generation model using Tensorflow Keras.

Code for the paper: Adversarial Machine Learning: Bayesian Perspectives

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

Perspective: Julia for Biologists

BabelCalib: A Universal Approach to Calibrating Central Cameras. In ICCV (2021)

Official implementation of paper Gradient Matching for Domain Generalization

[PNAS2021] The neural architecture of language: Integrative modeling converges on predictive processing

Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space"

efficient neural audio synthesis in the waveform domain

GoodNews Everyone! Context driven entity aware captioning for news images

Official implementation of the PICASO: Permutation-Invariant Cascaded Attentional Set Operator

City Surfaces: City-scale Semantic Segmentation of Sidewalk Surfaces

Smart edu-autobooking - Johnson @ DMI-UNICT study room self-booking system

Do Neural Networks for Segmentation Understand Insideness?

Learn other languages using artificial intelligence with python.

Code for unmixing audio signals in four different stems "drums, bass, vocals, others". The code is adapted from "Jukebox: A Generative Model for Music"

Related tags

Overview

Disclaimer

Unmix

Install

Training

Stage 1: VQVAE

Stage 2: Encoder

Train encoder

License (Jukebox OpenAI)

Owner

Wadhah Zai El Amri

PyTorch code for the "Deep Neural Networks with Box Convolutions" paper

Dataset and codebase for NeurIPS 2021 paper: Exploring Forensic Dental Identification with Deep Learning

Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.

This package implements the algorithms introduced in Smucler, Sapienza, and Rotnitzky (2020) to compute optimal adjustment sets in causal graphical models.

Automatic meme generation model using Tensorflow Keras.

Code for the paper: Adversarial Machine Learning: Bayesian Perspectives

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

Perspective: Julia for Biologists

BabelCalib: A Universal Approach to Calibrating Central Cameras. In ICCV (2021)

Official implementation of paper Gradient Matching for Domain Generalization

[PNAS2021] The neural architecture of language: Integrative modeling converges on predictive processing

Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space"

efficient neural audio synthesis in the waveform domain

GoodNews Everyone! Context driven entity aware captioning for news images

Official implementation of the PICASO: Permutation-Invariant Cascaded Attentional Set Operator

City Surfaces: City-scale Semantic Segmentation of Sidewalk Surfaces

Smart edu-autobooking - Johnson @ DMI-UNICT study room self-booking system

Do Neural Networks for Segmentation Understand Insideness?

Learn other languages ​​using artificial intelligence with python.

Learn other languages using artificial intelligence with python.