silero-vad-v6.2.1 (Vokra GGUF)

Voice activity detection model, 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
silero-vad-v6.2.1.gguf	2.1 MB	c86d36d0aa08eec97f124ad791f6556d6712558c3f2253cfeaaf58fa7db16f0b

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o silero-vad-v6.2.1.gguf \
  https://huggingface.co/vokra/silero-vad-v6.2.1/resolve/main/silero-vad-v6.2.1.gguf

vokra-cli run --model silero-vad-v6.2.1.gguf --input speech.wav

Prints the detected speech segments. Input must be mono 16 kHz WAV.

Provenance

Field	Value
Architecture	silero-vad
Tensors	30
Upstream source	snakers4/silero-vad v6.2.1 (MIT)
Upstream licence	MIT
Licence class	permissive
Registry model id	silero-vad-v6.2.1
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 silero-vad-v6.2.1.gguf
# expect: c86d36d0aa08eec97f124ad791f6556d6712558c3f2253cfeaaf58fa7db16f0b