rnnoise-v0.2 (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
rnnoise-v0.2.gguf	1.3 MB	2371a2e24d0112e93d740fb44628edd3373ad232a63fa6c7af090e9e56560de6

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o rnnoise-v0.2.gguf \
  https://huggingface.co/vokra/rnnoise-v0.2/resolve/main/rnnoise-v0.2.gguf

vokra-cli run --model rnnoise-v0.2.gguf --input input.wav

Provenance

Field	Value
Architecture	rnnoise
Tensors	1
Upstream source	https://github.com/xiph/rnnoise/releases/tag/v0.2
Upstream licence	bsd-3-clause
Licence class	permissive
Registry model id	rnnoise-v0.2
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 bsd-3-clause, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Verifying this file

shasum -a 256 rnnoise-v0.2.gguf
# expect: 2371a2e24d0112e93d740fb44628edd3373ad232a63fa6c7af090e9e56560de6