focalcodec-50hz (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
focalcodec-50hz.gguf	542.2 MB	3d19613193fe8cd4f3725209fa83c278e33d8b1e96fde43594b6c4328cf18d93

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o focalcodec-50hz.gguf \
  https://huggingface.co/vokra/focalcodec-50hz/resolve/main/focalcodec-50hz.gguf

vokra-cli run --model focalcodec-50hz.gguf --input input.wav

Provenance

Field	Value
Architecture	focalcodec
Tensors	354
Upstream source	lucadellalib/focalcodec_50hz (FocalCodec 50 Hz single-codebook audio codec, apache-2.0; base wavlm-large is MIT)
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	focalcodec-50hz
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 focalcodec-50hz.gguf
# expect: 3d19613193fe8cd4f3725209fa83c278e33d8b1e96fde43594b6c4328cf18d93