metadata
license: apache-2.0
library_name: vokra
tags:
- vokra
- gguf
xvector (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 |
|---|---|---|
xvector.gguf |
31.2 MB | a1aaad3efe781a45683cdec08bc0b4d5c7618f613ed3241be0d7230e6b28981a |
Usage
# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o xvector.gguf \
https://huggingface.co/vokra/xvector/resolve/main/xvector.gguf
vokra-cli run --model xvector.gguf --input input.wav
Provenance
| Field | Value |
|---|---|
| Architecture | xvector |
| Tensors | 46 |
| Upstream source | speechbrain/spkrec-xvect-voxceleb (TDNN X-vector speaker encoder, apache-2.0) |
| Upstream licence | apache-2.0 |
| Licence class | permissive |
| Registry model id | spkrec-xvect-voxceleb |
| 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 xvector.gguf
# expect: a1aaad3efe781a45683cdec08bc0b4d5c7618f613ed3241be0d7230e6b28981a