silero-vad-coreml

Silero VAD in CoreML format: the model Diction's on-device pipeline uses for voice activity detection on Apple hardware.

Credit

The Silero Team built the original VAD model (MIT). FluidInference built the CoreML conversion this is based on (pinned at revision b419383c). We publish it under our own namespace so Diction's runtime downloads, via FluidAudio, pin to a build we've tested instead of tracking FluidInference's default branch directly.

MIT licensed, as Silero VAD itself is.

Downloads last month
42
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support