vadonnx model mirror

ONNX Voice Activity Detection models served by vadonnx, mirrored here for reliable, self-hosted downloads. Files are byte-identical to their upstream sources.

Each model retains its own upstream license (Silero MIT, NVIDIA NeMo MarbleNet NVIDIA-OpenModelLicense, pyannote segmentation-3.0 MIT, FunASR FSMN MIT, SpeechBrain Apache-2.0, TEN Apache-2.0). See the vadonnx docs/licensing.md for details.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support