Giter Club home page Giter Club logo

wavenet-tf2's Introduction

WaveNet Tensorflow v2

WaveNet with TensorFlow 2.0

Train

Library

tensorflow
numpy
librosa
scipy
   ls wavs/*.wav | tail -n+10 > train_files.txt
   ls wavs/*.wav | head -n10 > test_files.txt
   python preprocess.py
   python train.py

Eval

   python synthesize.py [input_path] [output_path] [weight_path]

Result

The 1-day training model synsthesis result is below: 0001

pre trained model link is still a little way off.

Book

4a948f86-b96f-42ea-927f-14232d57589c_base_resized

https://techbookfest.org/product/5743005264773120
https://otakuassembly.booth.pm/items/1834753

References

WaveNet

論文。

r9y9/wavenet_vocoder
LESS IS MORE/WaveNet vocoder をやってみましたので、その記録です

いくつもの論文で使われている実装。PyTorch。

Rayhane-mamah/Tacotron-2

Tactron2 + WaveNetのDeepMindの人の実装。TensorFlow v1。

Monthly Hacker's Blog/VQ-VAEの追試で得たWaveNetのノウハウをまとめてみた。

WaveNetに関する知見が纏められている。

Synthesize Human Speech with WaveNet

Colabを用いた解説。Chainer。

The LJ Speech Dataset

英語の単一話者のデータセット。

JSUT

日本語の単一話者のデータセット。

wavenet-tf2's People

Contributors

kokeshing 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

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar

wavenet-tf2's Issues

synthesize.py error

when i run synthesize.py, ValueError: Input 0 of layer conv1d is incompatible with the layer: : expected min_ndim=3, found ndim=2. Full shape received: (1, 256) is occured. I think this error occured in synthesis function in wavenet class.

What is input_path?

Hi @kokeshing. Thank you for the very cool implementation of wavenet using tf2.
I'm trying to understand how to run your synthesize.py code and I would like to ask what the argument input_path is meant to be?

So output_path is where we want to save our generated data.
weight_path is where we have saved our trained model weights.
What is input_path meant to be and what is its purpose?

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.