Overview

The ced gguf model is a specialized audio classification tool optimized for local deployment via the GGUF format. Designed for developers who need efficient sound event detection without the overhead of heavy cloud dependencies, this model excels at categorizing audio signals into predefined classes. Its Apache-2.0 licensing makes it an ideal candidate for both open-source projects and commercial applications. Because it is distributed in GGUF, it integrates seamlessly with llama.cpp and other lightweight inference engines, allowing for low-latency audio analysis on edge devices or consumer-grade hardware. Compared to general-purpose audio models, ced focuses on classification accuracy and resource efficiency, making it suitable for real-time monitoring systems or automated audio tagging pipelines.

Highlights

Optimized GGUF format for efficient local inference
Specialized in high-accuracy audio signal classification
Permissive Apache-2.0 license for commercial use
Low-latency performance on edge computing hardware
Easy integration with llama.cpp and compatible runtimes

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("mudler/ced-gguf")
tokenizer = AutoTokenizer.from_pretrained("mudler/ced-gguf")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download mudler/ced-gguf

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download mudler/ced-gguf config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('mudler/ced-gguf')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/mudler/ced-gguf

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/mudler/ced-gguf

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('mudler/ced-gguf')
tokenizer = AutoTokenizer.from_pretrained('mudler/ced-gguf')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model mudler/ced-gguf

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model mudler/ced-gguf README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('mudler/ced-gguf')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/mudler/ced-gguf.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/mudler/ced-gguf.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'mudler/ced-gguf')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
library_name: ced.cpp
pipeline_tag: audio-classification
tags:
- audio-classification
- sound-event-detection
- audio-tagging
- audioset
- ggml
- gguf
- ced
base_model:
- mispeech/ced-tiny
- mispeech/ced-mini
- mispeech/ced-small
- mispeech/ced-base
---

CED (GGUF) for ced.cpp / LocalAI

GGUF quantizations of the CED family (Consistent Ensemble Distillation,
Xiaomi) - SOTA-tier audio-tagging models that classify everyday sounds (baby
cry, footsteps, glass breaking, alarms, dog bark, ...) into the 527-class
AudioSet ontology.

These files run with ced.cpp, a
standalone C++/ggml port (no Python, no
PyTorch at inference), and with LocalAI
via the ced backend. Converted from the mispeech/ced-* checkpoints
(Apache-2.0). CED is a plain AST/DeiT Vision Transformer over a log-mel
spectrogram; the port is numerically equal to the PyTorch reference.

Files

One self-contained GGUF per size + quant (config, 527 labels, and the mel
filterbank/window are all embedded). Pick by your accuracy/size budget:

| size | params | f16 | q8_0 | f32 |
|------|--------|-----|------|-----|
| tiny | 5.5M | ced-tiny-f16.gguf (11 MB) | ced-tiny-q8_0.gguf (6 MB) | - |
| mini | 9.6M | ced-mini-f16.gguf (19 MB) | ced-mini-q8_0.gguf (11 MB) | - |
| small | 22M | ced-small-f16.gguf (42 MB) | ced-small-q8_0.gguf (23 MB)| - |
| base | 86M | ced-base-f16.gguf (165 MB) | ced-base-q8_0.gguf (88 MB) | ced-base-f32.gguf (328 MB) |

tiny/q8_0 (6 MB) is ideal for Raspberry-Pi-class CPUs; base/f16 is the
accuracy default.

Parity vs PyTorch (ced-base, end-to-end probs)

| quant | max abs diff | top-5 tags |
|-------|--------------|------------|
| f32 | 1.7e-7 | identical |
| f16 | 6.4e-5 | identical |
| q8_0 | 6.0e-3 | identical |

Performance (CPU, ced-base, 10s clip, Ryzen 9 9950X3D, 4 threads)

| | latency | realtime factor | peak RSS |
|---|---|---|---|
| PyTorch (transformers, f32) | 155.7 ms | 65x | 717 MB |
| ced.cpp f16 | 100.6 ms | 100x | 189 MB |
| ced.cpp q8_0 | 117.2 ms | 86x | 111 MB |

ced.cpp f16 is ~1.55x faster than the PyTorch reference; q8_0 uses ~6.5x less
memory.

Usage

sh

ced-cli classify ced-base-f16.gguf clip.wav --top-k 5
0.87  Baby cry, infant cry
0.12  Crying, sobbing

In LocalAI: install the ced backend, configure a model with one of these
GGUFs, then call POST /v1/audio/classification (or stream over the realtime
websocket API for live recognition).

License

Model weights: Apache-2.0 (© Xiaomi Corporation; from the mispeech/ced-*
checkpoints). AudioSet labels are CC-BY-4.0. The ced.cpp inference code is MIT.