CED
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.
- Developer
- Xiaomi, China
- First release
- Nov 2023
- Latest release
- Mar 2026
- Sizes
- 5.5M - 86M
- License
- Commercial use allowedApache 2.0
- Ready-made builds
- 8-bit
- Running
- On your own serverAlso runs without a GPU
- Industries
- Manufacturing and logistics, Security, Software development, Media and production
What it does
- Labelling sound on modest hardware and on site
- Detecting alarm sounds and abnormal noise
- Fine-tuning for your own set of equipment sounds
- Picking fragments out of a continuous recording
Where it is used
Hardware requirements
Versions
- Обновление карточек моделей
- Сборки ONNX и INT8 в sherpa-onnx
- CED-Tiny, CED-Small, CED-Base
- CED-Mini
How to run it
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 CED 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 CED 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 CED support Russian?
Language does not matter for this model: it does not work with text.
Where can I download CED and what does it cost?
The CED 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
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
The classic set of convolutional networks that label sound across the 527 AudioSet categories, from machinery noise and alarms to breaking glass and screams. The system does not make a diagnosis, it gives you a reason to check the unit before it fails. A microphone can also capture people voices, which is personal data, so check the procedure with a lawyer.
DetailsMusic and soundAST (Audio Spectrogram Transformer)MIT · USACommercial use allowedA 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 monitoringDashengXiaomi · ChinaCommercial use allowedA 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.
DetailsSource: huggingface.co/mispeech/ced-base. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


