sgmse-voicebank (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
sgmse-voicebank.gguf	250.3 MB	33881190d635611fe9094f7eb3b37639be7c2df85db67cf91340b4a5a322d93e

Usage

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

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

Provenance

Field	Value
Architecture	sgmse
Tensors	647
Upstream source	speechbrain/sgmse-voicebank (SGMSE score-based diffusion speech enhancement, VoiceBank-DEMAND, apache-2.0)
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	sgmse-voicebank
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 sgmse-voicebank.gguf
# expect: 33881190d635611fe9094f7eb3b37639be7c2df85db67cf91340b4a5a322d93e