deepfake-audio-detection-v2 (Vokra GGUF)

Converted to the Vokra GGUF format for Vokra, a zero-dependency speech-AI inference runtime.

This is a conversion, not a new model. The weights are the upstream ones; Vokra re-packages them so its runtime can memory-map them directly. Credit for the model belongs upstream — see Source below.

Files

File	Size	SHA-256
deepfake-detection.gguf	360.8 MB	aa190afeb56f57042c8104d43b49b094e1efda069b7072e6e6d220894f7d4cf7

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o deepfake-detection.gguf \
  https://huggingface.co/vokra/deepfake-audio-detection-v2/resolve/main/deepfake-detection.gguf

vokra-cli run --model deepfake-detection.gguf --input input.wav

Provenance

Field	Value
Architecture	deepfake_detection
Tensors	215
Upstream source	MelodyMachine/Deepfake-audio-detection-V2 (WavLM binary classifier for audio deepfake detection, apache-2.0)
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	deepfake-audio-detection-v2
Vokra GGUF schema	1
Converted by	vokra-core 0.1.0-alpha.0

Every row above is read out of this file's own vokra.* metadata, so the card cannot claim something the artifact does not carry.

Licence

The weights are distributed under apache-2.0, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Verifying this file

shasum -a 256 deepfake-detection.gguf
# expect: aa190afeb56f57042c8104d43b49b094e1efda069b7072e6e6d220894f7d4cf7