Vetted New WebGPU

Voice activity detection model for onnxruntime-web (fp16). Runs on WASM or WebGPU — 1.2 MB downloaded once from models.skillsafe.ai, then cached for every SkillSafe app that uses it. Inference happens on your device; nothing you enter is uploaded to load it, and it never costs a credit. Weights from Hugging Face · skillsafe-ai/silero-vad, pinned at ab3ea3fe49d6 — also loadable straight from Hugging Face outside SkillSafe (how).

Share

Details

Catalogue idsilero-vad-fp16@v5-60b7ffa2
Runtimeonnxruntime-web ≥ 1.17.0
DeviceWASM, WebGPU
Variantfp16
Download1.2 MB · 1 file
LicenceMIT · notice
Pinned atab3ea3fe49d65c053c7d281e91d5981ff9c7a939
ApprovedSep 22, 2026
Statusactive — every file is a live vetted hash

Files

Each file is served at an immutable URL; the canonical form is the SHA-256 itself. Tokenizer and config JSON are not here by design — they ship in your app bundle.

PathFormatSizeSHA-256
silero_vad_half.onnx onnx 1.2 MB 1e0b195ad480…47c769

Signature

Graph inputs and outputs read from the ONNX bytes at vetting — the tensor names your session.run() call feeds and reads. Symbolic dimensions are shown by name.

Inputs

  • input float32 [batch, sequence]
  • state float32 [2, batch, 128]

Outputs

  • output float32 [batch, 1]
  • stateN float32 [ConcatstateN_dim_0, batch, ConcatstateN_dim_2]
Use it in an app declaration · SDK loader · onnxruntime-web · URLs · Hugging Face — generated from this entry

Add to the body of POST /v1/apps/{slug}/releases (or a release session). An unknown or withdrawn model is refused with a 400 naming it; the app page then shows "downloads 1.2 MB · runs on your device" and /models.txt carries the attribution.

{
  "models": [
    {
      "id": "silero-vad-fp16",
      "revision": "v5-60b7ffa2"
    }
  ]
}

Evaluation

onnx.checker + onnxruntime CPU smoke run with zero-filled inputs at the declared shapes; per-file SHA-256 pinned to the source — imported as published upstream, then checked. Evaluated Sep 22, 2026.

Runs under onnxruntime

Zero-filled inputs at the declared shapes, CPU execution provider on the converter host; the check is that the graph loads, runs, and emits the declared output shapes.

  • silero_vad.onnx: input[1,576], state[2,1,128], sr[] → output[1,1], stateN[2,1,128] 0.3 ms
  • silero_vad_half.onnx: input[1,576], state[2,1,128] → output[1,1], stateN[2,1,128] 0.2 ms

Toolchain: python 3.12.13 · platform Darwin 25.6.0 arm64 · torch 2.10.0 · onnx 1.23.0 · onnxruntime 1.30.0. Recipe models/recipes/silero-vad.yaml (add4c06a8242). Full manifest.json

Licence & attribution

MIT · licence text · notice

Silero VAD: Copyright (c) 2020-present Silero Team. MIT License. https://github.com/snakers4/silero-vad

Apps that declare this model get this text in their generated /models.txt, so a licence that requires a notice always carries one.

Every file here was approved by exact SHA-256 after a structural audit of the graph, fetched from a content-pinned source, and is served credential-free at an immutable URL. The SDK re-verifies the hash on your device before it caches or returns anything. Missing a variant? Request it — or read how the registry works.