SAVRN
Search Contact SAVRN

Open-weight model · Audio classification

ced-gguf

by Mudler mudler/ced-gguf

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.

Parameters—
Context—
Weights722.8 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads1M

Model Card

By Mudler, published under apache-2.0, revision b5e9a4aad643.

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

Read Mudler's full model card

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

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.

Identity and Version

Repository
mudler/ced-gguf
Publisher
Mudler
Task
Audio classification
Modality
Audio
Library
ced.cpp
Parameters
Not stated by the source
Languages
ced
Revision
b5e9a4aad6438763c8da16079d77563fbed35c65
First published
2026-06-21
Last updated
2026-06-21

Files and Weights

11 files, 722.8 MB in total. The weights are 9 files totalling 722.8 MB in gguf.

Weights9 files · 722.8 MB
Documentation1 file · 2.8 KB
Repository1 file · 2.0 KB
Every file
FileTypeSizeSHA-256
ced-base-f16.ggufWeights172.3 MB 5c058d9f7b73
ced-base-f32.ggufWeights342.9 MB 288a8cecc91c
ced-base-q8_0.ggufWeights92.3 MB bd34a7710169
ced-mini-f16.ggufWeights19.7 MB 3c6a8936c773
ced-mini-q8_0.ggufWeights10.8 MB 7062cef9ca31
ced-small-f16.ggufWeights43.7 MB c391ed8697a1
ced-small-q8_0.ggufWeights23.6 MB 888275fe4349
ced-tiny-f16.ggufWeights11.3 MB af8b81c67bae
ced-tiny-q8_0.ggufWeights6.2 MB 48bee4e2fc3c
README.mdDocumentation2.8 KB —
.gitattributesRepository2.0 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
722.8 MB
Download from Mudler

Released by Mudler through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published722.8 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About ced-gguf

Can I use ced-gguf commercially?

Yes. ced-gguf is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Audio classification

lang-id-voxlingua107-ecapa

SpeechBrain

This is a spoken language recognition model trained on the VoxLingua107 dataset using SpeechBrain. The model uses the ECAPA-TDNN architecture that has previously been used for speaker recognition. However, it uses more fully connected hidden layers after the embedding layer, and cross-entropy loss was used for training. We observed that this improved the performance of extracted utterance embeddings for downstream tasks. The system is trained with recordings sampled at 16kHz (single channel). The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling classifyfile if needed. The model can classify a speech utterance according to the language…

Open weights apache-2.0 speechbrain
View model

Model · Audio classification

accent-id-commonaccent_ecapa

Juan Pablo Zuluaga

Abstract: The recognition of accented speech still remains a dominant problem in Automatic Speech Recognition (ASR) systems. We approach the classification of accented English speech through the Emphasized Channel Attention, Propagation and Aggregation Time Delay Neural Network (ECAPA-TDNN) architecture which has been shown to perform well on a variety of speech tasks. Three models are proposed: one trained from scratch, another two models (one using data augmentation and a baseline model) fine-tuned from the checkpoints of speechbrain/spkrec-ecapa-voxceleb (VoxCeleb). Our results show that the model fine-tuned with data augmentation yield the best results. Most of the misclassifications…

Open weights mit speechbrain
View model

Model · Audio classification

MERT-v1-330M

Multimodal Art Projection

The development log of our Music Audio Pre-training (m-a-p) model family: - 02/06/2023: arxiv pre-print and training codes released. - 17/03/2023: we release two advanced music understanding models, MERT-v1-95M and MERT-v1-330M, trained with new paradigm and dataset. They outperform the previous models and can better generalize to more tasks. - 14/03/2023: we retrained the MERT-v0 model with open-source-only music dataset MERT-v0-public - 29/12/2022: a music understanding model MERT-v0 trained with MLM paradigm, which performs better at downstream tasks. - 29/10/2022: a pre-trained MIR model music2vec trained with BYOL paradigm. Here is a table for quick model pick-up: The m-a-p models…

Open weights cc-by-nc-4.0 transformers
View model

Model · Audio classification

MERT-v1-95M

Multimodal Art Projection

The development log of our Music Audio Pre-training (m-a-p) model family: - 02/06/2023: arxiv pre-print and training codes released. - 17/03/2023: we release two advanced music understanding models, MERT-v1-95M and MERT-v1-330M, trained with new paradigm and dataset. They outperform the previous models and can better generalize to more tasks. - 14/03/2023: we retrained the MERT-v0 model with open-source-only music dataset MERT-v0-public - 29/12/2022: a music understanding model MERT-v0 trained with MLM paradigm, which performs better at downstream tasks. - 29/10/2022: a pre-trained MIR model music2vec trained with BYOL paradigm. Here is a table for quick model pick-up: The m-a-p models…

Open weights cc-by-nc-4.0 transformers
View model

Model · Audio classification

gender_cls_svm_ecapa_voxceleb

Gregory Koushnir

This model combines the SpeechBrain ECAPA-TDNN speaker embedding model with an SVM classifier to predict speaker gender from audio input. The model was trained and evaluated on the VoxCeleb2, Mozilla Common Voice v10.0, and TIMIT datasets - Mozilla Common Voice v10.0 English validated test set: 92.3% accuracy The model was trained on VoxCeleb2 dataset: - Converted to WAV format, single channel, 16kHz sampling rate, 256 kp/s bitrate - Applied SileroVAD for voice activity detection, taking the first voiced segment You can install the package directly from GitHub: - Model was trained on celebrity voices from YouTube interviews - Performance may vary on different audio qualities or recording…

Open weights apache-2.0
View model

Model · Audio classification

wav2vec2-base-superb-er

Superb

This is a ported version of The base model is wav2vec2-base, which is pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. For more information refer to SUPERB: Speech processing Universal PERformance Benchmark Emotion Recognition (ER) predicts an emotion class for each utterance. The most widely used ER dataset IEMOCAP is adopted, and we follow the conventional evaluation protocol: we drop the unbalanced emotion classes to leave the final four classes with a similar amount of data points and cross-validate on five folds of the standard splits. For the original model's training and evaluation instructions refer to the You…

Open weights apache-2.0 transformers
View model