Lars Ulrich Challenge

Algorithmic and AI MIDI Drums Generator Implementation


Take LUC quickly with the official Jupyter/Colab Notebook

Open In Colab


❤️🥁 Performance Piano-Drums Output Sample (Algorithmic) 🥁❤️

NOTE: Do not forget to unmute the player below to hear the music

LUC-Main-Sample.mp4



Model Stats

Model trained on 70951 Pitches-Drums pairs from clean_midi/LAKH MIDI Datasets

Clean MIDI Transformer Model Raw Training Stats

Epoch: 1 Loss: 0.02231 LR: 0.00012121694: 100%|██████████| 132924/132924 [2:49:01<00:00, 13.11it/s] 
Loss val: 0.01247  Acc: 0.9957:  23%|██▎       | 922/3988 [00:31<01:43, 29.57it/s]


License/Attribution

The Lakh MIDI Dataset is distributed with a CC-BY 4.0 license; if you use this data in any capacity, please reference this page and my thesis:

Colin Raffel. “Learning-Based Methods for Comparing Sequences, with Applications to Audio-to-MIDI Alignment and Matching”. PhD Thesis, 2016.

Of course, I did not transcribe any of the MIDI files in the Lakh MIDI Dataset. While MIDI files have a built-in mechanism for attribution (the Copyright meta-event), it is not used consistently, so attributing each of the MIDI files in the dataset to a particular author is not feasible.

https://colinraffel.com/projects/lmd/


Citation

@inproceedings{lev2021larsulrichchallenge,
    title       = {Lars Ulrich Challenge},
    author      = {Aleksandr Lev},
    booktitle   = {GitHub},
    year        = {2021},
}

Project Los Angeles

Tegridy Code 2021

GitHub

View Github