Implementation of Google Brain's WaveGrad high-fidelity vocoder

Overview

alt-text-1

WaveGrad

Implementation (PyTorch) of Google Brain's high-fidelity WaveGrad vocoder (paper). First implementation on GitHub with high-quality generation for 6-iterations.

Status

  • Documented API.
  • High-fidelity generation.
  • Multi-iteration inference support (stable for low iterations).
  • Stable and fast training with mixed-precision support.
  • Distributed training support.
  • Training also successfully runs on a single 12GB GPU with batch size 96.
  • CLI inference support.
  • Flexible architecture configuration for your own data.
  • Estimated RTF on popular GPU and CPU devices (see below).
  • 100- and lower-iteration inferences are faster than real-time on RTX 2080 Ti. 6-iteration inference is faster than one reported in the paper.
  • Parallel grid search for the best noise schedule.
  • Uploaded generated samples for different number of iterations (see generated_samples folder).
  • Pretrained checkpoint on 22KHz LJSpeech dataset with noise schedules.

Real-time factor (RTF)

Number of parameters: 15.810.401

Model Stable RTX 2080 Ti Tesla K80 Intel Xeon 2.3GHz*
1000 iterations + 9.59 - -
100 iterations + 0.94 5.85 -
50 iterations + 0.45 2.92 -
25 iterations + 0.22 1.45 -
12 iterations + 0.10 0.69 4.55
6 iterations + 0.04 0.33 2.09

*Note: Used an old version of Intel Xeon CPU.


About

WaveGrad is a conditional model for waveform generation through estimating gradients of the data density with WaveNet-similar sampling quality. This vocoder is neither GAN, nor Normalizing Flow, nor classical autoregressive model. The main concept of vocoder is based on Denoising Diffusion Probabilistic Models (DDPM), which utilize Langevin dynamics and score matching frameworks. Furthemore, comparing to classic DDPM, WaveGrad achieves super-fast convergence (6 iterations and probably lower) w.r.t. Langevin dynamics iterative sampling scheme.


Installation

  1. Clone this repo:
git clone https://github.com/ivanvovk/WaveGrad.git
cd WaveGrad
  1. Install requirements:
pip install -r requirements.txt

Training

1 Preparing data

  1. Make train and test filelists of your audio data like ones included into filelists folder.
  2. Make a configuration file* in configs folder.

*Note: if you are going to change hop_length for STFT, then make sure that the product of your upsampling factors in config is equal to your new hop_length.

2 Single and Distributed GPU training

  1. Open runs/train.sh script and specify visible GPU devices and path to your configuration file. If you specify more than one GPU the training will run in distributed mode.
  2. Run sh runs/train.sh

3 Tensorboard and logging

To track your training process run tensorboard by tensorboard --logdir=logs/YOUR_LOGDIR_FOLDER. All logging information and checkpoints will be stored in logs/YOUR_LOGDIR_FOLDER. logdir is specified in config file.

4 Noise schedule grid search

Once model is trained, grid search for the best schedule* for a needed number of iterations in notebooks/inference.ipynb. The code supports parallelism, so you can specify more than one number of jobs to accelerate the search.

*Note: grid search is necessary just for a small number of iterations (like 6 or 7). For larger number just try Fibonacci sequence benchmark.fibonacci(...) initialization: I used it for 25 iteration and it works well. From good 25-iteration schedule, for example, you can build a higher-order schedule by copying elements.

Noise schedules for pretrained model
  • 6-iteration schedule was obtained using grid search. After, based on obtained scheme, by hand, I found a slightly better approximation.
  • 7-iteration schedule was obtained in the same way.
  • 12-iteration schedule was obtained in the same way.
  • 25-iteration schedule was obtained using Fibonacci sequence benchmark.fibonacci(...).
  • 50-iteration schedule was obtained by repeating elements from 25-iteration scheme.
  • 100-iteration schedule was obtained in the same way.
  • 1000-iteration schedule was obtained in the same way.

Inference

CLI

Put your mel-spectrograms in some folder. Make a filelist. Then run this command with your own arguments:

sh runs/inference.sh -c <your-config> -ch <your-checkpoint> -ns <your-noise-schedule> -m <your-mel-filelist> -v "yes"

Jupyter Notebook

More inference details are provided in notebooks/inference.ipynb. There you can also find how to set a noise schedule for the model and make grid search for the best scheme.


Other

Generated audios

Examples of generated audios are provided in generated_samples folder. Quality degradation between 1000-iteration and 6-iteration inferences is not noticeable if found the best schedule for the latter.

Pretrained checkpoints

You can find a pretrained checkpoint file* on LJSpeech (22KHz) via this Google Drive link.

*Note: uploaded checkpoint is a dict with a single key 'model'.


Important details, issues and comments

  • During training WaveGrad uses a default noise schedule with 1000 iterations and linear scale betas from range (1e-6, 0.01). For inference you can set another schedule with less iterations. Tune betas carefully, the output quality really highly depends on it.
  • By default model runs in a mixed-precision way. Batch size is modified compared to the paper (256 -> 96) since authors trained their model on TPU.
  • After ~10k training iterations (1-2 hours) on a single GPU the model performs good generation for 50-iteration inference. Total training time is about 1-2 days (for absolute convergence).
  • At some point training might start to behave weird and crazy (loss explodes), so I have introduced learning rate (LR) scheduling and gradient clipping. If loss explodes for your data, then try to decrease LR scheduler gamma a bit. It should help.
  • By default hop length of your STFT is equal 300 (thus total upsampling factor). Other cases are not tested, but you can try. Remember, that total upsampling factor should be still equal to your new hop length.

History of updates

  • (NEW: 10/24/2020) Huge update. Distributed training and mixed-precision support. More correct positional encoding. CLI support for inference. Parallel grid search. Model size significantly decreased.
  • New RTF info for NVIDIA Tesla K80 GPU card (popular in Google Colab service) and CPU Intel Xeon 2.3GHz.
  • Huge update. New 6-iteration well generated sample example. New noise schedule setting API. Added the best schedule grid search code.
  • Improved training by introducing smarter learning rate scheduler. Obtained high-fidelity synthesis.
  • Stable training and multi-iteration inference. 6-iteration noise scheduling is supported.
  • Stable training and fixed-iteration inference with significant background static noise left. All positional encoding issues are solved.
  • Stable training of 25-, 50- and 1000-fixed-iteration models. Found no linear scaling (C=5000 from paper) of positional encoding (bug).
  • Stable training of 25-, 50- and 1000-fixed-iteration models. Fixed positional encoding downscaling. Parallel segment sampling is replaced by full-mel sampling.
  • (RELEASE, first on GitHub). Parallel segment sampling and broken positional encoding downscaling. Bad quality with clicks from concatenation from parallel-segment generation.

References

Owner
Ivan Vovk
• Mathematics • Machine Learning • Speech technologies
Ivan Vovk
Composable transformations of Python+NumPy programsComposable transformations of Python+NumPy programs

Chex Chex is a library of utilities for helping to write reliable JAX code. This includes utils to help: Instrument your code (e.g. assertions) Debug

DeepMind 506 Jan 08, 2023
Python package for visualizing the loss landscape of parameterized quantum algorithms.

orqviz A Python package for easily visualizing the loss landscape of Variational Quantum Algorithms by Zapata Computing Inc. orqviz provides a collect

Zapata Computing, Inc. 75 Dec 30, 2022
Binary classification for arrythmia detection with ECG datasets.

HEART DISEASE AI DATATHON 2021 [Eng] / [Kor] #English This is an AI diagnosis modeling contest that uses the heart disease echocardiography and electr

HY_Kim 3 Jul 14, 2022
Multistream CNN for Robust Acoustic Modeling

Multistream Convolutional Neural Network (CNN) A multistream CNN is a novel neural network architecture for robust acoustic modeling in speech recogni

ASAPP Research 37 Sep 21, 2022
Advanced yabai wooting scripts

Yabai Wooting scripts Installation requirements Both https://github.com/xiamaz/python-yabai-client and https://github.com/xiamaz/python-wooting-rgb ne

Max Zhao 3 Dec 31, 2021
Hypersearch weight debugging and losses tutorial

tutorial Activate tensorboard option Running TensorBoard remotely When working on a remote server, you can use SSH tunneling to forward the port of th

1 Dec 11, 2021
High-Resolution Image Synthesis with Latent Diffusion Models

Latent Diffusion Models Requirements A suitable conda environment named ldm can be created and activated with: conda env create -f environment.yaml co

CompVis Heidelberg 5.6k Jan 04, 2023
Code for reproducing our paper: LMSOC: An Approach for Socially Sensitive Pretraining

LMSOC: An Approach for Socially Sensitive Pretraining Code for reproducing the paper LMSOC: An Approach for Socially Sensitive Pretraining to appear a

Twitter Research 11 Dec 20, 2022
Multi-Scale Geometric Consistency Guided Multi-View Stereo

ACMM [News] The code for ACMH is released!!! [News] The code for ACMP is released!!! About ACMM is a multi-scale geometric consistency guided multi-vi

Qingshan Xu 118 Jan 04, 2023
This repository contains the source code and data for reproducing results of Deep Continuous Clustering paper

Deep Continuous Clustering Introduction This is a Pytorch implementation of the DCC algorithms presented in the following paper (paper): Sohil Atul Sh

Sohil Shah 197 Nov 29, 2022
LUKE -- Language Understanding with Knowledge-based Embeddings

LUKE (Language Understanding with Knowledge-based Embeddings) is a new pre-trained contextualized representation of words and entities based on transf

Studio Ousia 587 Dec 30, 2022
Code for the ICME 2021 paper "Exploring Driving-Aware Salient Object Detection via Knowledge Transfer"

TSOD Code for the ICME 2021 paper "Exploring Driving-Aware Salient Object Detection via Knowledge Transfer" Usage For training, open train_test, run p

Jinming Su 2 Dec 23, 2021
Another pytorch implementation of FCN (Fully Convolutional Networks)

FCN-pytorch-easiest Trying to be the easiest FCN pytorch implementation and just in a get and use fashion Here I use a handbag semantic segmentation f

Y. Dong 158 Dec 21, 2022
OHLC Average Prediction of Apple Inc. Using LSTM Recurrent Neural Network

Stock Price Prediction of Apple Inc. Using Recurrent Neural Network OHLC Average Prediction of Apple Inc. Using LSTM Recurrent Neural Network Dataset:

Nouroz Rahman 410 Jan 05, 2023
Code for Robust Contrastive Learning against Noisy Views

Robust Contrastive Learning against Noisy Views This repository provides a PyTorch implementation of the Robust InfoNCE loss proposed in paper Robust

Ching-Yao Chuang 53 Jan 08, 2023
Simple tutorials on Pytorch DDP training

pytorch-distributed-training Distribute Dataparallel (DDP) Training on Pytorch Features Easy to study DDP training You can directly copy this code for

Ren Tianhe 188 Jan 06, 2023
Training deep models using anime, illustration images.

animeface deep models for anime images. Datasets anime-face-dataset Anime faces collected from Getchu.com. Based on Mckinsey666's dataset. 63.6K image

Tomoya Sawada 61 Dec 25, 2022
Code for CVPR 2021 paper: Anchor-Free Person Search

Introduction This is the implementationn for Anchor-Free Person Search in CVPR2021 License This project is released under the Apache 2.0 license. Inst

158 Jan 04, 2023
Gray Zone Assessment

Gray Zone Assessment Get started Clone github repository git clone https://github.com/andreanne-lemay/gray_zone_assessment.git Build docker image dock

1 Jan 08, 2022
Approaches to modeling terrain and maps in python

topography 🌎 Contains different approaches to modeling terrain and topographic-style maps in python Features Inverse Distance Weighting (IDW) A given

John Gutierrez 1 Aug 10, 2022