Acoustic monitoringMusic and sound

Dasheng

A general-purpose audio encoder trained on 272 thousand hours of speech, music and noise: it gives features on top of which you train your own classifier of abnormal sounds. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.

Developer
Xiaomi, China
First release
Jun 2024
Latest release
Mar 2026
Sizes
86M - 1.2B
License
Commercial use allowedApache 2.0
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

  • Audio features for your own anomaly model
  • Finding similar fragments in a recording archive
  • Fine-tuning for the sounds of one production line
  • Labelling sound events on a site

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. Шумоподавитель на базе Dasheng
  2. Dasheng-0.6B и Dasheng-1.2B
  3. Dasheng-Base

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 Dasheng be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Dasheng 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 Dasheng support Russian?

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

Where can I download Dasheng and what does it cost?

The Dasheng 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

Acoustic 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.

DetailsAcoustic monitoringBEATsMicrosoft · USACommercial use allowed

A self-supervised sound understanding model that became the base for many current systems: teams take it as a starting point and fine-tune it on their own equipment sounds. The system does not make a diagnosis, it gives you a reason to check the unit before it fails.

DetailsMusic and soundCLAP (LAION)LAION · GermanyCommercial use allowed

CLIP for audio: maps audio and text into a shared space. Lets you search sounds and music by description and classify them without training. Text must be in English.

Details

Source: huggingface.co/mispeech/dasheng-base. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.