Giter Club home page Giter Club logo

waveglow's Introduction

WaveGlow

A PyTorch implementation of the WaveGlow: A Flow-based Generative Network for Speech Synthesis

Quick Start:

  1. Install requirements:
pip install -r requirements.txt
  1. Download dataset:
wget http://festvox.org/cmu_arctic/cmu_arctic/packed/cmu_us_slt_arctic-0.95-release.tar.bz2
tar xf cmu_us_slt_arctic-0.95-release.tar.bz2

  1. Extract features: feature extracting pipeline is the same as tacotron

  2. Training with default hyperparams:

python train.py
  1. Synthesize from model:
python generate.py --checkpoint=/path/to/model --local_condition_file=/path/to/local_conditon

Notes:

  • This is not official implementation, some details are not necessarily correct.
  • Work in progress.

waveglow's People

Contributors

npuichigo avatar ss18 avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Forkers

g-wang zhang-jian haifengzeng toannhu hcwu1993 wyn314 johndpope ml-lab ss18 donghaiyw ruimina huguanglong vshalts samangel93 yueyedeai qoboty qianqq dachengai xiaochunan gridl qq1074123922 eos21 intuitionmachine quocvuong82 o7s8r6 linlinsongyun xushengyuan kedengfeng entn-at hologerry silyfox jakatar zhangyuewei98 chestnut-fish chelseamilton

waveglow's Issues

Undefined name: Where is _GetFileAndLine() defined?

https://github.com/npuichigo/waveglow/search?q=_GetFileAndLine

flake8 testing of https://github.com/npuichigo/waveglow on Python 3.7.1

$ flake8 . --count --select=E901,E999,F821,F822,F823 --show-source --statistics

./waveglow/logging.py:144:38: F821 undefined name '_GetFileAndLine'
    count = _GetNextLogCountPerToken(_GetFileAndLine())
                                     ^
./waveglow/logging.py:157:38: F821 undefined name '_GetFileAndLine'
    count = _GetNextLogCountPerToken(_GetFileAndLine())
                                     ^
2     F821 undefined name '_GetFileAndLine'
2

Early Output implementation is same as the paper?

Hi,

It's a nice work!
I found that you output half of current channels for early output. But in the paper, they output constant channels for early output. In their case, output 2 channels.
Am I wrong? Or there are some tricks?

synthesis time

How long does it take to synthesise 1 second of audio? Is is like the paper, faster than realtime?

数据集问题

你好，按照该仓库REDEME中的介绍，索引到tactron中数据处理的方法，但是好像数据命名问题是不一致的，也许是tactron中数据处理的部分更新了。
请问有没有其他数据预处理的模块。或者提供下数据集样式，谢谢！

negative loss value

i'm using your code to train my dataset,the codes ran ok while loss value is negative ,is this normal?

INFO:pytorch:Let's use 1 GPUs!
C:\Python35\lib\site-packages\torch\nn\modules\upsampling.py:122: UserWarning: nn.Upsampling is deprecated. Use nn.functional.interpolate instead.
  warnings.warn("nn.Upsampling is deprecated. Use nn.functional.interpolate instead.")
INFO:pytorch:[1,   1] loss: 8774.103
INFO:pytorch:[1,   2] loss: 247.321
INFO:pytorch:[1,   3] loss: 2267.624
INFO:pytorch:[1,   4] loss: 2223.914
INFO:pytorch:[1,   5] loss: 21230.785
INFO:pytorch:[1,   6] loss: -4516.562
INFO:pytorch:[1,   7] loss: -1636.356
INFO:pytorch:[1,   8] loss: -1802.424
INFO:pytorch:[1,   9] loss: -973.106
INFO:pytorch:[1,  10] loss: -2390.099
INFO:pytorch:[1,  11] loss: -3500.059
INFO:pytorch:[1,  12] loss: -2850.755
INFO:pytorch:[1,  13] loss: -4785.271
INFO:pytorch:[1,  14] loss: -5666.863
INFO:pytorch:[1,  15] loss: -6398.563
INFO:pytorch:[1,  16] loss: 6809.037
INFO:pytorch:[1,  17] loss: 6204.096
INFO:pytorch:[1,  18] loss: -9287.712
INFO:pytorch:[1,  19] loss: -3614.344

How to choose upsampling rte for conditioning?

@npuichigo

I have local conditioning of following shape 1 X 1000 X 50 (for 1 sec) with input speech of 16k sampling rate. Can you recommend, which up sampling factor I should choose ? and How to estimate up sampling factor ?
Thanks

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.