PyTorch implementation of SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

Overview

samplernn-pytorch

A PyTorch implementation of SampleRNN: An Unconditional End-to-End Neural Audio Generation Model.

A visual representation of the SampleRNN architecture

It's based on the reference implementation in Theano: https://github.com/soroushmehr/sampleRNN_ICLR2017. Unlike the Theano version, our code allows training models with arbitrary number of tiers, whereas the original implementation allows maximum 3 tiers. However it doesn't allow using LSTM units (only GRU). For more details and motivation behind rewriting this model to PyTorch, see our blog post: http://deepsound.io/samplernn_pytorch.html.

Dependencies

This code requires Python 3.5+ and PyTorch 0.1.12+. Installation instructions for PyTorch are available on their website: http://pytorch.org/. You can install the rest of the dependencies by running pip install -r requirements.txt.

Datasets

We provide a script for creating datasets from YouTube single-video mixes. It downloads a mix, converts it to wav and splits it into equal-length chunks. To run it you need youtube-dl (a recent version; the latest version from pip should be okay) and ffmpeg. To create an example dataset - 4 hours of piano music split into 8 second chunks, run:

cd datasets
./download-from-youtube.sh "https://www.youtube.com/watch?v=EhO_MrRfftU" 8 piano

You can also prepare a dataset yourself. It should be a directory in datasets/ filled with equal-length wav files. Or you can create your own dataset format by subclassing torch.utils.data.Dataset. It's easy, take a look at dataset.FolderDataset in this repo for an example.

Training

To train the model you need to run train.py. All model hyperparameters are settable in the command line. Most hyperparameters have sensible default values, so you don't need to provide all of them. Run python train.py -h for details. To train on the piano dataset using the best hyperparameters we've found, run:

python train.py --exp TEST --frame_sizes 16 4 --n_rnn 2 --dataset piano

The results - training log, loss plots, model checkpoints and generated samples will be saved in results/.

We also have an option to monitor the metrics using CometML. To use it, just pass your API key as --comet_key parameter to train.py.

Owner
DeepSound
DeepSound is a project of creating a system capable of generating music using deep learning methods, led by two students pursuing their Master's degree.
DeepSound
Official implementation of particle-based models (GNS and DPI-Net) on the Physion dataset.

Physion: Evaluating Physical Prediction from Vision in Humans and Machines [paper] Daniel M. Bear, Elias Wang, Damian Mrowca, Felix J. Binder, Hsiao-Y

Hsiao-Yu Fish Tung 18 Dec 19, 2022
A PyTorch implementation of EfficientDet.

A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights

Ross Wightman 1.4k Jan 07, 2023
Learning kernels to maximize the power of MMD tests

Code for the paper "Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy" (arXiv:1611.04488; published at ICLR 2017), by Douga

Danica J. Sutherland 201 Dec 17, 2022
Aspect-Sentiment-Multiple-Opinion Triplet Extraction (NLPCC 2021)

The code and data for the paper "Aspect-Sentiment-Multiple-Opinion Triplet Extraction" Requirements Python 3.6.8 torch==1.2.0 pytorch-transformers==1.

慢半拍 5 Jul 02, 2022
Code for A Volumetric Transformer for Accurate 3D Tumor Segmentation

VT-UNet This repo contains the supported pytorch code and configuration files to reproduce 3D medical image segmentaion results of VT-UNet. Environmen

Himashi Amanda Peiris 114 Dec 20, 2022
Efficiently computes derivatives of numpy code.

Note: Autograd is still being maintained but is no longer actively developed. The main developers (Dougal Maclaurin, David Duvenaud, Matt Johnson, and

Formerly: Harvard Intelligent Probabilistic Systems Group -- Now at Princeton 6.1k Jan 08, 2023
From the basics to slightly more interesting applications of Tensorflow

TensorFlow Tutorials You can find python source code under the python directory, and associated notebooks under notebooks. Source code Description 1 b

Parag K Mital 5.6k Jan 09, 2023
How to use TensorLayer

How to use TensorLayer While research in Deep Learning continues to improve the world, we use a bunch of tricks to implement algorithms with TensorLay

zhangrui 349 Dec 07, 2022
Collections for the lasted paper about multi-view clustering methods (papers, codes)

Multi-View Clustering Papers Collections for the lasted paper about multi-view clustering methods (papers, codes). There also exists some repositories

Andrew Guan 10 Sep 20, 2022
PyTorch evaluation code for Delving Deep into the Generalization of Vision Transformers under Distribution Shifts.

Out-of-distribution Generalization Investigation on Vision Transformers This repository contains PyTorch evaluation code for Delving Deep into the Gen

Chongzhi Zhang 72 Dec 13, 2022
Jax/Flax implementation of Variational-DiffWave.

jax-variational-diffwave Jax/Flax implementation of Variational-DiffWave. (Zhifeng Kong et al., 2020, Diederik P. Kingma et al., 2021.) DiffWave with

YoungJoong Kim 37 Dec 16, 2022
Official PyTorch(Geometric) implementation of DPGNN(DPGCN) in "Distance-wise Prototypical Graph Neural Network for Node Imbalance Classification"

DPGNN This repository is an official PyTorch(Geometric) implementation of DPGNN(DPGCN) in "Distance-wise Prototypical Graph Neural Network for Node Im

Yu Wang (Jack) 18 Oct 12, 2022
Keeping it safe - AI Based COVID-19 Tracker using Deep Learning and facial recognition

Keeping it safe - AI Based COVID-19 Tracker using Deep Learning and facial recognition

Vansh Wassan 15 Jun 17, 2021
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

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

Phil Wang 12.6k Jan 09, 2023
The PyTorch implementation of paper REST: Debiased Social Recommendation via Reconstructing Exposure Strategies

REST The PyTorch implementation of paper REST: Debiased Social Recommendation via Reconstructing Exposure Strategies. Usage Download dataset Download

DMIRLAB 2 Mar 13, 2022
vit for few-shot classification

Few-Shot ViT Requirements PyTorch (= 1.9) TorchVision timm (latest) einops tqdm numpy scikit-learn scipy argparse tensorboardx Pretrained Checkpoints

Martin Dong 26 Nov 30, 2022
Company clustering with K-means/GMM and visualization with PCA, t-SNE, using SSAN relation extraction

RE results graph visualization and company clustering Installation pip install -r requirements.txt python -m nltk.downloader stopwords python3.7 main.

Jieun Han 1 Oct 06, 2022
Simulator for FRC 2022 challenge: Rapid React

rrsim Simulator for FRC 2022 challenge: Rapid React out-1.mp4 Usage In order to run the simulator use the following: python3 rrsim.py [config_path] wh

1 Jan 18, 2022
AI Summer's complete catalog of articles

Learn Deep Learning with AI Summer A collection of all articles (almost 100) written for the AI Summer blog organized by topic. Deep Learning Theory M

AI Summer 95 Dec 29, 2022
IEGAN — Official PyTorch Implementation Independent Encoder for Deep Hierarchical Unsupervised Image-to-Image Translation

IEGAN — Official PyTorch Implementation Independent Encoder for Deep Hierarchical Unsupervised Image-to-Image Translation Independent Encoder for Deep

30 Nov 05, 2022