Acoustic monitoringMusic and sound

DASS

A sound understanding model built on state spaces instead of a transformer: it handles recordings hours long, which suits continuous listening to a production line. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.

Developer
MIT CSAIL and MIT-IBM Watson AI Lab, USA
First release
Jul 2024
Latest release
Apr 2025
Sizes
30M (small) and 49M (medium)
License
Commercial use allowedBSD 3-Clause
Running
On your own serverAlso runs without a GPU
Industries
Manufacturing and logistics, Security, Media and production, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Processing long continuous recordings
  • Finding a rare event across a multi-hour shift
  • Labelling sound events on a site
  • Fine-tuning on your own equipment sounds

Where it is used

Manufacturing and equipment maintenanceSite securityMedia and audio archivesResearch

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
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Обновлённые веса small и medium
  2. Веса DASS small и medium на Hugging Face
  3. DASS, статья и код

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.

Frequently asked questions

Can DASS be used in a commercial project?

Yes. License: BSD 3-Clause. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does DASS 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 DASS support Russian?

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

Where can I download DASS and what does it cost?

The DASS 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 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.

DetailsAcoustic monitoringEATShanghai Jiao Tong University and Peng Cheng Laboratory · ChinaCommercial use allowed

A self-supervised sound understanding model that is markedly cheaper to train on your own data than its predecessors. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.

DetailsAcoustic monitoringCEDXiaomi · ChinaCommercial use allowed

Compact sound-labelling models from 5.5M to 86M, with ONNX and INT8 builds that run on an ordinary CPU and on a board next to the equipment. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.

Details

Source: huggingface.co/saurabhati/DASS_medium_AudioSet_50.2. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.