Giter Site home page Giter Site logo

francesclluis / source-separation-wavenet Goto Github PK

View Code? Open in Web Editor NEW
220.0 15.0 34.0 84.16 MB

A neural network for end-to-end music source separation

License: MIT License

Python 100.00%
machine-learning deep-learning neural-networks source-separation wavenet audio-processing karaoke vocal-remover

source-separation-wavenet's Issues

musDB interface change

The correct line to retrieve the data from the dataset after extraction is

mus = musdb.DB(root=self.path, is_wav=True)

instead of

mus = musdb.DB(root_dir=self.path, is_wav=True)

Running this in real time on an audio stream

Hey!
First of all I want to thank you for publishing this awesome work.

In the readme you mention, that this is capable of doing real time source separation when run on a GPU. I'm really really interested in that use case.
However I can only find ways to give it input wav files and no way to tell it to use i.e. an audio device from the PC.

I'm assuming that this functionality hasn't been implemented yet. Would it be trivial to do so?

Judging by https://github.com/francesclluis/source-separation-wavenet/blob/master/separate.py#L82 there is some kind of minimal amount of samples one would have to give the network.
Thus would it be feasible to say pass it every new frame of sound data with the last few frames also attached to make it work on an audio stream?

Or is there a way to maybe feed to the network frame by frame? that would be awesome because then one wouldn't have to deal with stitching the different results back together which would probably result in some quirkiness.

I would be happy to contribute this feature, but want to make sure it's possible first :D

theano not using GPU

Hi.

I was wondering how I can use GPU for training?

I checked with tutorial theano python code and confirmed it uses GPU.

However, when I run wavenet, it does not use GPU and instead uses CPU.

Could you share how I can use GPU?

Thanks

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.