nsnet2 (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
nsnet2.gguf	10.3 MB	abeca882165909fb0897b39b97882d0ebd9f95cf176a4d2e58482e52a8b19e13

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o nsnet2.gguf \
  https://huggingface.co/vokra/nsnet2/resolve/main/nsnet2.gguf

vokra-cli run --model nsnet2.gguf --input input.wav

Provenance

Field	Value
Architecture	nsnet2
Tensors	14
Upstream source	Microsoft DNS-Challenge NSNet2-baseline (MIT end-to-end)
Upstream licence	mit
Licence class	permissive
Registry model id	nsnet2-20ms-baseline
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 nsnet2.gguf
# expect: abeca882165909fb0897b39b97882d0ebd9f95cf176a4d2e58482e52a8b19e13