Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
The NES Music Database: use machine learning to compose music for the Nintendo Entertainment System!
| Date | Stars |
|---|---|
| 2026-07-31 | 503 |
| 2026-08-05 | 503 |
| 2026-08-06 | 503 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
The NES Music Database ====================== - [Dataset information](#dataset-information) - [Download links](#download-links) - [MIDI format](#midi-format) - [Score formats](#score-formats) - [Language modeling format](#language-modeling-format) - [`nesmdb` Python package](#nesmdb-package-information) - [Installation](#installation) - [Render audio](#rendering-audio) - [NES synthesizer primer](#nes-synthesizer-primer) - [Attribution](#attribution) The Nintendo Entertainment System Music Database (NES-MDB) is a dataset intended for building automatic music composition systems for the NES audio synthesizer ([paper](https://arxiv.org/abs/1806.04278)). The NES synthesizer has highly constrained compositional parameters which are well-suited to a wide variety of current machine learning techniques. The synthesizer is typically programmed in [assembly](https://wiki.nesdev.com/w/index.php/APU), but we parse the assembly into straightforward formats that are more suitable for machine learning. This repository contains dataset information as well as `nesmdb`, a Python package that can be used to render your generated music through the NES synthesizer. **You only need to [install](#package-installation) the `nesmdb` package if you want to listen to your generated results.** Otherwise, you may simply [download](#download-links) an appropriate format of the dataset. ## Dataset information The NES-MDB dataset consists of 5278 songs from the soundtracks of 397 NES games. The dataset represents 296 unique composers, and the songs contain more than two million notes combined. We build NES-MDB starting from the assembly code of NES games, which contain the exact timings and parameter values necessary for accurate chiptune renditions. We split the dataset into training, validation, and testing splits, ensuring that no composer appears in multiple splits. The NES synthesizer has five instrument voices: two pulse-wave generators (`P1`, `P2`), a triangle-wave generator (`TR`), a percussive noise generator (`NO`), and an audio sample playback channel (excluded for simplicity). Each voice is programmed by modifying four 8-bit registers which update the audio synthesis state. With NES-MDB, **our goal is to allow researchers to study NES music while shielding them from the inner workings of an archaic audio synthesis chip**. Hence, we offer the dataset in [several convenient formats](#download-links), and [provide details](#nes-synthesizer-primer) for those who wish to dig deeper. If your background is in **algorithmic composition**, we recommend using either the [**MIDI**](#midi-format) or [**score**](#score-formats) formats. If you are more familiar with **language modeling**, we recommend the [**NES Language Modeling**](#language-modeling-format) (NLM) format. ### Download links Hover download links for SHA256 checksums. - `( 12 MB)` [Download](https://drive.google.com/file/d/1w2uo1Cmio4gz6nGUhZOtzF54kPkoKyo7/view?usp=drive_link "37610e2ca5fe70359c85170cf1f4982596783bb304c59d9c439f68c24ff4ee93") NES-MDB in [MIDI Format](#midi-format) - `( 11 MB)` [Download](https://drive.google.com/file/d/1i2HdWsxPEjBUtsMclioqC7nmN9aCDwRc/view?usp=drive_link "7ca09fdf2be6db5c0767ef6ef7f3f4cac06ae23336c463d123009681b9d64d50") NES-MDB in [Expressive Score Format](#expressive-score) - `( 04 MB)` [Download](https://drive.google.com/file/d/1I-HHMDBcpiVNoxkkT7kt94ZchZZ0aR-T/view?usp=drive_link "3e2dadfc0b499cc730a7d2143705215e6cf5abec9e75e6a3e6131f4f9fefeb3a") NES-MDB in [Separated Score Format](#separated-score) - `( 41 MB)` [Download](https://drive.google.com/file/d/1Eon6mzhSg9gL_uRv8XgWvgpFCxIT5Mb0/view?usp=drive_link "d72027bdbf91fd983963136199c9d60e7b2c6dca8cd461c04bd97ca14425893d") NES-MDB in [Blended Score Format](#blended-score) - `(155 MB)` [Download](https://drive.google.com/file/d/1FaPCfBZoeGt_1O6JsJm8hkYLX_yoRRpF/view?usp=drive_link "5e37a6fe3fa3bb96c93e0d938d89df2767ddfc9d3153b6de6c11f5b9d57bd3a3") NES-MDB in [Language Modeling Format
Excerpt of 20,514 characters
Read on GitHub
68
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:938f0769f308ef83, llm:description: 'The NES Music Database: use machine learning to compose music for the Nintendo Entertainment System!'
matched fp:938f0769f308ef83, llm:description: 'The NES Music Database: use machine learning to compose music for the Nintendo Entertainment System!'