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

Overview

NU-Wave — Official PyTorch Implementation

NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
Junhyeok Lee, Seungu Han @ MINDsLab Inc., SNU

Paper(arXiv): https://arxiv.org/abs/2104.02321 (Accepted to INTERSPEECH 2021)
Audio Samples: https://mindslab-ai.github.io/nuwave

Official Pytorch+Lightning Implementation for NU-Wave.

Update: CODE RELEASED! README is DONE.

Requirements

Preprocessing

Before running our project, you need to download and preprocess dataset to .pt files

  1. Download VCTK dataset
  2. Remove speaker p280 and p315
  3. Modify path of downloaded dataset data:dir in hparameters.yaml
  4. run utils/wav2pt.py
$ python utils/wav2pt.py

Training

  1. Adjust hparameters.yaml, especially train section.
train:
  batch_size: 18 # Dependent on GPU memory size
  lr: 0.00003
  weight_decay: 0.00
  num_workers: 64 # Dependent on CPU cores
  gpus: 2 # number of GPUs
  opt_eps: 1e-9
  beta1: 0.5
  beta2: 0.999
  • If you want to train with single speaker, use VCTKSingleSpkDataset instead of VCTKMultiSpkDataset for dataset in dataloader.py. And use batch_size=1 for validation dataloader.
  • Adjust data section in hparameters.yaml.
data:
  dir: '/DATA1/VCTK/VCTK-Corpus/wav48/p225' #dir/spk/format
  format: '*mic1.pt'
  cv_ratio: (223./231., 8./231., 0.00) #train/val/test
  1. run trainer.py.
$ python trainer.py
  • If you want to resume training from checkpoint, check parser.
    parser = argparse.ArgumentParser()
    parser.add_argument('-r', '--resume_from', type =int,\
            required = False, help = "Resume Checkpoint epoch number")
    parser.add_argument('-s', '--restart', action = "store_true",\
            required = False, help = "Significant change occured, use this")
    parser.add_argument('-e', '--ema', action = "store_true",\
            required = False, help = "Start from ema checkpoint")
    args = parser.parse_args()
  • During training, tensorboard logger is logging loss, spectrogram and audio.
$ tensorboard --logdir=./tensorboard --bind_all

Evaluation

run for_test.py or test.py

$ python test.py -r {checkpoint_number} {-e:option, if ema} {--save:option}
or
$ python for_test.py -r {checkpoint_number} {-e:option, if ema} {--save:option}

Please check parser.

    parser = argparse.ArgumentParser()
    parser.add_argument('-r', '--resume_from', type =int,
                required = True, help = "Resume Checkpoint epoch number")
    parser.add_argument('-e', '--ema', action = "store_true",
                required = False, help = "Start from ema checkpoint")
    parser.add_argument('--save', action = "store_true",
               required = False, help = "Save file")

While we provide lightning style test code test.py, it has device dependency. Thus, we recommend to use for_test.py.

References

This implementation uses code from following repositories:

This README and the webpage for the audio samples are inspired by:

The audio samples on our webpage are partially derived from:

Repository Structure

.
├── Dockerfile
├── dataloader.py           # Dataloader for train/val(=test)
├── filters.py              # Filter implementation
├── test.py                 # Test with lightning_loop.
├── for_test.py             # Test with for_loop. Recommended due to device dependency of lightning
├── hparameter.yaml         # Config
├── lightning_model.py      # NU-Wave implementation. DDPM is based on ivanvok's WaveGrad implementation
├── model.py                # NU-Wave model based on lmnt-com's DiffWave implementation
├── requirement.txt         # requirement libraries
├── sampling.py             # Sampling a file
├── trainer.py              # Lightning trainer
├── README.md           
├── LICSENSE
├── utils
│  ├── stft.py              # STFT layer
│  ├── tblogger.py          # Tensorboard Logger for lightning
│  └── wav2pt.py            # Preprocessing
└── docs                    # For github.io
   └─ ...

Citation & Contact

If this repository useful for your research, please consider citing! Bibtex will be updated after INTERSPEECH 2021 conference.

@article{lee2021nuwave,
  title={NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling},
  author={Lee, Junhyeok and Han, Seungu},
  journal={arXiv preprint arXiv:2104.02321},
  year={2021}
}

If you have a question or any kind of inquiries, please contact Junhyeok Lee at [email protected]

Owner
MINDs Lab
MINDsLab provides AI platform and various AI engines based on deep machine learning.
MINDs Lab
NAS-FCOS: Fast Neural Architecture Search for Object Detection (CVPR 2020)

NAS-FCOS: Fast Neural Architecture Search for Object Detection This project hosts the train and inference code with pretrained model for implementing

Ning Wang 180 Dec 06, 2022
Oscar and VinVL

Oscar: Object-Semantics Aligned Pre-training for Vision-and-Language Tasks VinVL: Revisiting Visual Representations in Vision-Language Models Updates

Microsoft 938 Dec 26, 2022
Code for "MetaMorph: Learning Universal Controllers with Transformers", Gupta et al, ICLR 2022

MetaMorph: Learning Universal Controllers with Transformers This is the code for the paper MetaMorph: Learning Universal Controllers with Transformers

Agrim Gupta 50 Jan 03, 2023
CryptoFrog - My First Strategy for freqtrade

cryptofrog-strategies CryptoFrog - My First Strategy for freqtrade NB: (2021-04-20) You'll need the latest freqtrade develop branch otherwise you migh

Robert Davey 137 Jan 01, 2023
Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift (ICCV 2021)

Π-NAS This repository provides the evaluation code of our submitted paper: Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training

Jiqi Zhang 18 Aug 18, 2022
Hypercomplex Neural Networks with PyTorch

HyperNets Hypercomplex Neural Networks with PyTorch: this repository would be a container for hypercomplex neural network modules to facilitate resear

Eleonora Grassucci 21 Dec 27, 2022
The code for paper "Learning Implicit Fields for Generative Shape Modeling".

implicit-decoder The tensorflow code for paper "Learning Implicit Fields for Generative Shape Modeling", Zhiqin Chen, Hao (Richard) Zhang. Project pag

Zhiqin Chen 353 Dec 30, 2022
Neural style transfer as a class in PyTorch

pt-styletransfer Neural style transfer as a class in PyTorch Based on: https://github.com/alexis-jacq/Pytorch-Tutorials Adds: StyleTransferNet as a cl

Tyler Kvochick 31 Jun 27, 2022
Your interactive network visualizing dashboard

Your interactive network visualizing dashboard Documentation: Here What is Jaal Jaal is a python based interactive network visualizing tool built usin

Mohit 177 Jan 04, 2023
The authors' implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations This is the authors' implementation of Unsupervised Adversarial Learning of

Dwango Media Village 140 Dec 07, 2022
DetCo: Unsupervised Contrastive Learning for Object Detection

DetCo: Unsupervised Contrastive Learning for Object Detection arxiv link News Sparse RCNN+DetCo improves from 45.0 AP to 46.5 AP(+1.5) with 3x+ms trai

Enze Xie 234 Dec 18, 2022
Implementation for NeurIPS 2021 Submission: SparseFed

READ THIS FIRST This repo is an anonymized version of an existing repository of GitHub, for the AIStats 2021 submission: SparseFed: Mitigating Model P

2 Jun 15, 2022
Supervised & unsupervised machine-learning techniques are applied to the database of weighted P4s which admit Calabi-Yau hypersurfaces.

Weighted Projective Spaces ML Description: The database of 5-vectors describing 4d weighted projective spaces which admit Calabi-Yau hypersurfaces are

Ed Hirst 3 Sep 08, 2022
The official PyTorch implementation for NCSNv2 (NeurIPS 2020)

Improved Techniques for Training Score-Based Generative Models This repo contains the official implementation for the paper Improved Techniques for Tr

174 Dec 26, 2022
Hub is a dataset format with a simple API for creating, storing, and collaborating on AI datasets of any size.

Hub is a dataset format with a simple API for creating, storing, and collaborating on AI datasets of any size. The hub data layout enables rapid transformations and streaming of data while training m

Activeloop 5.1k Jan 08, 2023
Joint Learning of 3D Shape Retrieval and Deformation, CVPR 2021

Joint Learning of 3D Shape Retrieval and Deformation Joint Learning of 3D Shape Retrieval and Deformation Mikaela Angelina Uy, Vladimir G. Kim, Minhyu

Mikaela Uy 38 Oct 18, 2022
Proposed n-stage Latent Dirichlet Allocation method - A Novel Approach for LDA

n-stage Latent Dirichlet Allocation (n-LDA) Proposed n-LDA & A Novel Approach for classical LDA Latent Dirichlet Allocation (LDA) is a generative prob

Anıl Güven 4 Mar 07, 2022
Back to Event Basics: SSL of Image Reconstruction for Event Cameras

Back to Event Basics: SSL of Image Reconstruction for Event Cameras Minimal code for Back to Event Basics: Self-Supervised Learning of Image Reconstru

TU Delft 42 Dec 26, 2022
Unifying Global-Local Representations in Salient Object Detection with Transformer

GLSTR (Global-Local Saliency Transformer) This is the official implementation of paper "Unifying Global-Local Representations in Salient Object Detect

11 Aug 24, 2022
Live training loss plot in Jupyter Notebook for Keras, PyTorch and others

livelossplot Don't train deep learning models blindfolded! Be impatient and look at each epoch of your training! (RECENT CHANGES, EXAMPLES IN COLAB, A

Piotr Migdał 1.2k Jan 08, 2023