GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → salu133445 → lakh-pianoroll-dataset

salu133445 / lakh-pianoroll-dataset

Licence: MIT license
A collection of 174,154 multi-track piano-rolls

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Labels

musicmusic-information-retrievalmusic-generationmultitrackpianoroll

Projects that are alternatives of or similar to lakh-pianoroll-dataset

MidiTok
A convenient MIDI / symbolic music tokenizer for Deep Learning networks, with multiple strategies 🎶
Stars: ✭ 180 (+181.25%)
Mutual labels:  music-information-retrieval, music-generation
hum2song
Hum2Song: Multi-track Polyphonic Music Generation from Voice Melody Transcription with Neural Networks
Stars: ✭ 61 (-4.69%)
Mutual labels:  music-generation
Tutorial
Tutorial covering Open Source tools for Source Separation.
Stars: ✭ 223 (+248.44%)
Mutual labels:  music-information-retrieval
musicntwrk
Network Analysis of Generalized Musical Spaces
Stars: ✭ 37 (-42.19%)
Mutual labels:  music-information-retrieval
ACA-Slides
Slides and Code for "An Introduction to Audio Content Analysis," also taught at Georgia Tech as MUSI-6201. This introductory course on Music Information Retrieval is based on the text book "An Introduction to Audio Content Analysis", Wiley 2012/2022
Stars: ✭ 84 (+31.25%)
Mutual labels:  music-information-retrieval
toscanini
A JavaScript module for searching music scores.
Stars: ✭ 15 (-76.56%)
Mutual labels:  music-information-retrieval
Dali
DALI: a large Dataset of synchronised Audio, LyrIcs and vocal notes.
Stars: ✭ 193 (+201.56%)
Mutual labels:  music-information-retrieval
alda-clj
A Clojure library for live-coding music with Alda
Stars: ✭ 54 (-15.62%)
Mutual labels:  music-generation
bmusegan
Code for “Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation”
Stars: ✭ 58 (-9.37%)
Mutual labels:  music-generation
da-tacos
A Dataset for Cover Song Identification and Understanding
Stars: ✭ 50 (-21.87%)
Mutual labels:  music-information-retrieval
Dyci2Lib
"Dicy2 for Max" is a Max package implementing interactive agents using machine-learning to generate musical sequences that can be integrated into musical situations ranging from the production of structured material within a compositional process to the design of autonomous agents for improvised interaction. Check also our plugin for Ableton live !
Stars: ✭ 35 (-45.31%)
Mutual labels:  music-generation
ismir2019-music-style-translation
The code for the ISMIR 2019 paper “Supervised symbolic music style translation using synthetic data”.
Stars: ✭ 27 (-57.81%)
Mutual labels:  music-information-retrieval
Catch-A-Waveform
Official pytorch implementation of the paper: "Catch-A-Waveform: Learning to Generate Audio from a Single Short Example" (NeurIPS 2021)
Stars: ✭ 117 (+82.81%)
Mutual labels:  music-generation
Gist
A C++ Library for Audio Analysis
Stars: ✭ 244 (+281.25%)
Mutual labels:  music-information-retrieval
wavegan-pytorch
Pytorch Implementation of wavegan model to generate audio
Stars: ✭ 97 (+51.56%)
Mutual labels:  music-generation
Olaf
Olaf: Overly Lightweight Acoustic Fingerprinting is a portable acoustic fingerprinting system.
Stars: ✭ 198 (+209.38%)
Mutual labels:  music-information-retrieval
emusic net
Neural network to classify certain styles of Electronic music
Stars: ✭ 22 (-65.62%)
Mutual labels:  music-information-retrieval
spafe
🔉 spafe: Simplified Python Audio Features Extraction
Stars: ✭ 310 (+384.38%)
Mutual labels:  music-information-retrieval
music-genre-classification
Zalo AI Challenge - Music Genre Classification
Stars: ✭ 23 (-64.06%)
Mutual labels:  music-information-retrieval
CLMR
Official PyTorch implementation of Contrastive Learning of Musical Representations
Stars: ✭ 216 (+237.5%)
Mutual labels:  music-information-retrieval
View All Similar Projects ➔

Source Code for Deriving Lakh Pianoroll Dataset (LPD)

The derived dataset using the default settings is available here.

  1. Download Lakh MIDI Dataset (LMD) with the following script.

    ./scripts/download_lmd.sh

    (Or, download it manually here.)

  2. Set the variables LMD_ROOT and LPD_ROOT in run.sh and variables in config.py to proper values.

  3. Derive all subsets and versions of LPD, matched_ids.txt and cleansed_ids.txt with the following script.

    ./scripts/derive_lpd.sh

Derive the labels for the LPD

The derived labels can be found at data/labels.tar.gz.

  1. Download the labels with the following script.

    ./scripts/download_labels.sh

  2. Derive the labels with the following script.

    ./scripts/derive_labels.sh

Synthesize audio files for the LPD

  1. Install GNU Parallel to run the synthesizer in parallel mode.

  2. Synthesize audio files from multitrack pianorolls with the following script.

    ./scripts/batch_synthesize.sh ./data/lpd/lpd/lpd_cleansed/ \
  ./data/synthesized/lpd_cleansed 20

    (The above command will synthesize all the multitrack pianorolls in the LPD-cleansed subset with 20 parallel jobs.)

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].