# FMA: A Dataset For Music Analysis

arXiv: https://arxiv.org/abs/1612.01840 · HTML: https://mlsanity.com/paper/1612.01840/

## Key facts

- Cited by 207 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2016.

## Built on by (most cited first, 30 of 207)

- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension](https://mlsanity.com/paper/2402.07729/) (2024)
- [Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities](https://mlsanity.com/paper/2402.01831/) (2024)
- [Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities](https://mlsanity.com/paper/2503.03983/) (2025)
- [WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling](https://mlsanity.com/paper/2408.16532/) (2024)
- [Joint Audio and Speech Understanding](https://mlsanity.com/paper/2309.14405/) (2023)
- [Mustango: Toward Controllable Text-to-Music Generation](https://mlsanity.com/paper/2311.08355/) (2023)
- [Long-form music generation with latent diffusion](https://mlsanity.com/paper/2404.10301/) (2024)
- [Contrastive Learning of Musical Representations](https://mlsanity.com/paper/2103.09410/) (2021)
- [DITTO: Diffusion Inference-Time T-Optimization for Music Generation](https://mlsanity.com/paper/2401.12179/) (2024)
- [Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model](https://mlsanity.com/paper/2408.17175/) (2024)
- [Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion](https://mlsanity.com/paper/2402.10009/) (2024)
- [WavMark: Watermarking for Audio Generation](https://mlsanity.com/paper/2308.12770/) (2023)
- [DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment](https://mlsanity.com/paper/2507.02768/) (2025)
- [AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?](https://mlsanity.com/paper/2412.02611/) (2024)
- [Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2505.15957/) (2025)
- [Foundation Models for Music: A Survey](https://mlsanity.com/paper/2408.14340/) (2024)
- [Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis](https://mlsanity.com/paper/2603.06507/) (2026)
- [LLark: A Multimodal Instruction-Following Language Model for Music](https://mlsanity.com/paper/2310.07160/) (2023)
- [Controllable Music Production with Diffusion Models and Guidance Gradients](https://mlsanity.com/paper/2311.00613/) (2023)
- [InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue](https://mlsanity.com/paper/2510.13747/) (2025)
- [Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey](https://mlsanity.com/paper/2412.18619/) (2024)
- [AudioMarkBench: Benchmarking Robustness of Audio Watermarking](https://mlsanity.com/paper/2406.06979/) (2024)
- [Nystr"om Kernel Mean Embeddings](https://mlsanity.com/paper/2201.13055/) (2022)
- [AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation](https://mlsanity.com/paper/2412.15191/) (2024)
- [Aligning Text-to-Music Evaluation with Human Preferences](https://mlsanity.com/paper/2503.16669/) (2025)
- [Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music](https://mlsanity.com/paper/2604.10905/) (2026)
- [Multi-Task Self-Supervised Pre-Training for Music Classification](https://mlsanity.com/paper/2102.03229/) (2021)
- [Sound Localization by Self-Supervised Time Delay Estimation](https://mlsanity.com/paper/2204.12489/) (2022)

## Abstract (arXiv)

We introduce the Free Music Archive (FMA), an open and easily accessible dataset suitable for evaluating several tasks in MIR, a field concerned with browsing, searching, and organizing large music collections. The community's growing interest in feature and end-to-end learning is however restrained by the limited availability of large audio datasets. The FMA aims to overcome this hurdle by providing 917 GiB and 343 days of Creative Commons-licensed audio from 106,574 tracks from 16,341 artists and 14,854 albums, arranged in a hierarchical taxonomy of 161 genres. It provides full-length and high-quality audio, pre-computed features, together with track- and user-level metadata, tags, and free-form text such as biographies. We here describe the dataset and how it was created, propose a train/validation/test split and three subsets, discuss some suitable MIR tasks, and evaluate some baselines for genre recognition. Code, data, and usage examples are available at https://github.com/mdeff/fma