Music and soundSearch and RAG

MERT

A music encoder: turns a track into a numeric representation used to detect genre, mood, key and rhythm. MERT-v2 handles full songs up to 6 minutes.

Developer
m-a-p (Multimodal Art Projection), UK / China
First release
Dec 2022
Latest release
Sep 2026
Sizes
95M – 632M
License
Non-commercial onlyCC-BY-NC 4.0 (non-commercial)
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Media and production, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Automatic tagging of a music catalog
  • Finding similar tracks
  • Detecting genre, mood and tempo

Where it is used

Music services and labelsMediaResearch

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. MERT-v2 (30s, FullSong)
  2. MERT-v1 (95M, 330M)
  3. MERT-v0

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can MERT be used in a commercial project?

No. License: CC-BY-NC 4.0 (non-commercial). A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does MERT need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does MERT support Russian?

Language does not matter for this model: it does not work with text.

Where can I download MERT and what does it cost?

The MERT weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Music and soundMuQ / MuQ-MuLanTencent AI Lab · ChinaNon-commercial only

The MuQ music encoder and the MuQ-MuLan model, which matches music and text: you can search for tracks by a description in English or Chinese.

DetailsMusic and soundAST (Audio Spectrogram Transformer)MIT · USACommercial use allowed

A classic 2021 sound recognition model: detects 527 AudioSet event classes (siren, barking, breaking glass, music). Lightweight, runs without a GPU, in Transformers since 2022.

DetailsComputer visionSigLIP (наследник CLIP)Google · USACommercial use allowed

Models that map images and text into a shared space: you can search photos by words and classify images without training. OpenAI's CLIP (2021) is the predecessor.

Details

Source: huggingface.co/m-a-p/MERT-v2-FullSong. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.