Trackdub Silero Vad FP16

--- license: mit base_model: onnx-community/silero-vad base_model_relation: quantized pipeline_tag: voice-activity-detection library_name: onnxruntime language: - multilingual tags: - onnx - onnxruntime - silero-vad - vad - voice-activity-detection - fp16 - audio --- # Silero VAD — FP16 ONNX FP16 ONNX export of Silero VAD, an open-weight voice activity detection model. The immediate upstream source is [onnx-community/silero-vad](https://huggingface.co/onnx-community/silero-vad); the original model is from the Silero team (snakers4/silero-vad on GitHub). This is not a newly trained model. ## Source | Field | Value | |---|---| | Upstream model | [onnx-community/silero-vad](https://huggingface.co/onnx-community/silero-vad) | | Upstream source revision | `e71cae966052b992a7eca6b17738916ce0eca4ec` | | Export tool/script | Mirrored from onnx-community (no re-export) | | Quantization recipe | FP16 ONNX mirrored from `onnx/model_fp16.onnx` | | Original model | [snakers4/silero-vad](https://github.com/snakers4/silero-vad) (GitHub) | ## Files | File | Size | Description | |---|---|---| | `onnx/model_fp16.onnx` | ~1 MB | FP16 ONNX model | ## Intended Use Voice activity detection for local inference via ONNX Runtime. VAD identifies segments of audio that contain speech versus silence or background noise. The FP16 variant targets GPU execution; the INT8 variant is in [`tonythethompson/silero-vad-int8-onnx`](https://huggingface.co/tonythethompson/silero-vad-int8-onnx). Silero VAD is language-agnostic and works across a wide range of languages. ## Runtime Notes - Designed for ONNX Runtime compatible runtimes. - Expected input: 16 kHz mono audio (Silero VAD requirement). - Execution: GPU (CUDA) preferred for FP16. Validate on the target execution provider before production use. ## Precision and Packaging Export tooling, precision, and quantization are recorded in the **Source** table above. This packaging mirror does not publish independent parity benchmarks; validate on your target execution provider before production use. ## Limitations - Requires 16 kHz mono audio input; other sample rates must be resampled. - FP16 precision may cause degraded detection on hardware that upcasts silently. - No repository-specific VAD quality benchmark is documented here. - Performance on very noisy or music-heavy audio is not evaluat...