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 budget:

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

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

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).

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.