Giter Club home page Giter Club logo

meowify's Introduction

Meowify

Turn vocals from any youtube song to meows!
The project was developed for HAMR 2020 in 48 hours and received the Best Hack/Research Direction award.

alt text

About

This is an initial release using the Flask microframework. Eventually, I aim to deploy it on heroku.

I wouldn't recommend running it without cuda, since ddsp.training.metrics.compute_audio_features will take too long, especially for long tracks.

DISCLAIMER: Thanks and credits to Magenta for providing DDSP and the colab notebooks that I used and modified for local use and Deezer for providing Spleeter.

Here is an example for "Dumb" by Nirvana

Installation

git clone https://github.com/gulnazaki/meowify.git
cd meowify
pip3 install -r requirements.txt

Running

flask run

visit localhost:5000, enter a youtube link and have fun

meowify's People

Contributors

gulnazaki avatar

Stargazers

Abdullah Shahid avatar Sayan B avatar Adrian Carballo avatar Rabqubit avatar  avatar Patricio Ovalle avatar  avatar Ethan Manilow avatar Taein KIM avatar Steph avatar Soroush Omranpour avatar Thomas Prätzlich avatar Theodoros Giannakopoulos avatar

Watchers

James Cloos avatar  avatar

meowify's Issues

Having issues running your program

Hello, I found this program would be great for a project I'm doing. Though I ran into a few problems and since I'm not a programmer and only have basic skills, I could not figure out the problem. The first issue was that the audio file would be downloaded from youtube, but the file went into the main folder as .m4a and I got the error as No such file or directory . To overcome this, I tried downloading the file directly and putting it into the folder as .wav . It worked as I got to the step where the audio would be split, that the "meowifying the vocals" part didn't work. I got "NameError: name 'write_to_file' is not defined" and couldn't figure out what to do.
Not sure what the error is, it could be something with google.colab, since I haven't been able to install module because 'Failed to build wheel for pandas' although i'm unusre if that module is even needed.

Would be cool if I could get it to work! Have a great day and sorry if I am being unprofessional, as I said I don't have much knowledge in this field.

Guidance on its usage

@gulnazaki
Hey Thomas,
We participated in HAMR2020 together where I made SInFork and you made meowify.I wanted to ask if I can work on something related to this and in a way a extension of this work where I wanted to add more animals then just cats like birds,dogs etc.

Also,Can you help with this issue of mine while trying to run this on Ubuntu 20.04:
When I try to :
pip3 install -r requirements.txt
Error:

ERROR: Cannot install -r requirements.txt (line 10) and -r requirements.txt (line 5) because these package versions have conflicting dependencies.

The conflict is caused by:
    google-colab 1.0.0 depends on pandas~=0.24.0
    spleeter 2.0 depends on pandas==1.1.2

To fix this you could try to:
1. loosen the range of package versions you've specified
2. remove package versions to allow pip attempt to solve the dependency conflict

ERROR: ResolutionImpossible: for help visit https://pip.pypa.io/en/latest/user_guide/#fixing-conflicting-dependencies

But then I try to manually install things,but the issue persists in various ways like sometime even after installing spleeter it show no module named spleeter,uninstalling already installed version of a package,etc

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.