ten-vad (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
ten-vad.gguf	0.3 MB	a0c5f7a89569dca5fa06de4050768cddf6cd456ddca785a3eb241699528c3f04

Usage

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

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

Provenance

Field	Value
Architecture	ten_vad
Tensors	19
Upstream source	github.com/TEN-framework/ten-vad (compact ~306 KB LSTM/GRU VAD + LPCNet-derived DSP front-end, Apache-2.0 main + BSD-3-Clause front-end — NOTICE attribution required for LPCNet copyright when redistributing binaries embedding the front-end)
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	ten_vad
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 ten-vad.gguf
# expect: a0c5f7a89569dca5fa06de4050768cddf6cd456ddca785a3eb241699528c3f04