deepfilternet3 (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
dfn3.gguf	8.2 MB	448c391760a5bc7e6acb63698796dadc959c7439cd2fb56cca59e0bdd7a68b1e

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o dfn3.gguf \
  https://huggingface.co/vokra/deepfilternet3/resolve/main/dfn3.gguf

vokra-cli run --model dfn3.gguf --input input.wav

Provenance

Field	Value
Architecture	denoise
Tensors	115
Upstream source	Rikorose/DeepFilterNet (MIT OR Apache-2.0)
Upstream licence	MIT OR Apache-2.0
Licence class	permissive
Registry model id	deepfilternet3
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 MIT OR Apache-2.0, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

The Hugging Face license: tag is set to other because MIT OR Apache-2.0 is not one of Hugging Face's accepted tag values. The authoritative licence is the one named above and reproduced in the LICENSE file — not the tag.

Verifying this file

shasum -a 256 dfn3.gguf
# expect: 448c391760a5bc7e6acb63698796dadc959c7439cd2fb56cca59e0bdd7a68b1e