CoolFace
Modelpublic

pat229988/spoof-pad-wavlm-nes2net-tflite

sourceHugging Faceotherupdated 3mo agoView on Hugging Face
0likes9downloads
Model Card

Spoof/PAD WavLM + Nes2Net-X TFLite

This repository contains a spoof / presentation-attack-detection model exported to TFLite/LiteRT for local CPU testing.

Files

FilePurpose
spoof_pad.tfliteRuntime TFLite flatbuffer.
spoof_pad.tflite.manifest.jsonConversion/runtime manifest.
artifact_manifest.jsonClean upload metadata, checksum, and source lineage.

Source lineage

This is a converted derivative of a WavLM + Nes2Net-X anti-spoofing stack:

  • —Active checkpoint repo: `nielsr/nes2net-checkpoints`
  • —Active checkpoint file: <https://huggingface.co/nielsr/nes2net-checkpoints/resolve/main/WavLMNes2NetXe75seed420_valid0.03192785031473534.pt?download=true>
  • —WavLM base model: `microsoft/wavlm-large`
  • —Original implementation repo / branch: <https://github.com/Liu-Tianchi/Nes2NetASVspoofITW/tree/asvspoof5>

GitHub implementation repos cannot be represented as Hugging Face base_model relationships, so they are listed explicitly here and in artifact_manifest.json.

Runtime contract

  • —Sample rate: 16000 Hz
  • —Input preprocessing: normalize to mono 16 kHz, then take/tile exactly 64600 samples
  • —Input dtype: float32
  • —Output: single logit interpreted as the bona-fide score
  • —Score direction: higher score is more bona-fide
  • —Thresholds are application-specific. Useful decision values include max_spoof_probability, min_bonafide_probability, and min_bonafide_logit.

Limitations

  • —This is an experimental converted artifact.
  • —License and usage terms must be checked against the upstream WavLM, Nes2Net, ASVspoof, and checkpoint sources before redistribution or production use.
  • —PAD thresholds are application-specific; validate on your target microphones, speakers, replay conditions, and attack types.