snac-24khz (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
model.gguf	75.7 MB	3c357841858fd24a05f4a7fb5b28daffa5931373aad3112f83a9d09d3575cc8a

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o model.gguf \
  https://huggingface.co/vokra/snac-24khz/resolve/main/model.gguf

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

Provenance

Field	Value
Architecture	snac
Tensors	269
Upstream source	hubertsiuzdak/snac_24khz (SNAC Multi-Scale Neural Audio Codec, 24 kHz, 3 RVQ levels @ ~12/23/47 Hz, mit)
Upstream licence	mit
Licence class	permissive
Registry model id	snac-24khz
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, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Verifying this file

shasum -a 256 model.gguf
# expect: 3c357841858fd24a05f4a7fb5b28daffa5931373aad3112f83a9d09d3575cc8a