silero-vad-v5 (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-v5.gguf | 2.1 MB | 23b19eadba72fb9726fa73a0bfd095afcba2f8c5bcb4f03a1b5e57a67eb13df6 |
Usage
# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o silero-vad-v5.gguf \
https://huggingface.co/vokra/silero-vad-v5/resolve/main/silero-vad-v5.gguf
vokra-cli run --model silero-vad-v5.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 v5 (MIT) |
| Upstream licence | MIT |
| Licence class | permissive |
| Registry model id | silero-vad-v5 |
| 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-v5.gguf
# expect: 23b19eadba72fb9726fa73a0bfd095afcba2f8c5bcb4f03a1b5e57a67eb13df6