Git Product home page Git Product logo

jamais-vu's Introduction

Jamaisvu

A work-in-progress improvement upon Will Drevo's Dejavu project for audio fingering printing in Python. The aim of Jamaisvu is to be optimised and effective enough to be used as a sound identifier for DJs at Lafayette College's WJRH Radio.

I occasionally write about the progress of Jamaisvu on my website, and features and bugs I am currently working on can be viewed on my Trello board

The main goals for Jamaisvu over Dejavu is:

  • Provide more features
    • Detailed Information about songs (e.g. Artist, Album, Explicit, etc...)
    • Support API calls to be able to run in the background
    • Provide support for user entry and modification for mislabelled data
  • Provide much faster fingerprinting times via optimisations and GPU acceleration
  • Be integrated with Renan Dincer's Teal, which is a nice package for organising and storing radio shows

Eventually this will be used as the backend for WJRH Assistant

Getting Started

Tested only on MacOS and Ubuntu 16.04

Prerequisites

What dependencies you will need to run Jamaisvu:

  • Numpy
  • Scipy
  • Pycuda
  • AcoustID
  • Mysql
  • Mysql-config
  • Spotipy (You will need to set this up with your own Spotify account and keys in your PATH!)
  • Pymsgbox
  • Pydub
  • Pyaudio (also portaudio19-dev)
  • Reikna
  • Scikit-cuda

Installing

Ensure that you have a MySQL Database instance setup and running on your local machine and then setup a database for Jamaisvu with:

$ mysql -u root -p
Enter password: **********
mysql> CREATE DATABASE IF NOT EXISTS jamaisvu;

Hello World

You can use the JMV_Test.py to test to make sure your installation is working correctly

$ python JMV_Test.py [path to config.yaml] [path to music file]

The programme should fingerprint your file, store it in the database, read the file again, and identify it using the database. It should return something like:

Result:
song_genre : canadian pop
confidence : 181436
offset_seconds : 0.0
match_time : 6.18130493164
offset : 0
song_artist : The Weeknd
song_id : 1
song_name : Often - Kygo Remix
file_sha1 : 4EC99324791D7AF5A497FB693FF1DD3DBD3420A1
song_album : Often (Kygo Remix)
song_length : 234400
song_explicit : 1

Acknowledgments

jamais-vu's People

Contributors

ajduberstein avatar bevinsky avatar bhuvi8 avatar chromy avatar compwright avatar cwbhx avatar fbrcosta avatar pguridi avatar sg3510 avatar suxianbaozi avatar thesunlover avatar tjj5036 avatar tuxdna avatar wessie avatar worldveil 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

Watchers

 avatar  avatar  avatar  avatar  avatar

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.