Kavach (कवच) — Real-Time Voice Impersonation Defense & Telephony Forensic Weights
Kavach is an open-source voice authenticity and anti-spoofing defense engine engineered specifically for real-time telephony, WebRTC live audio streams, and financial vishing prevention.
Model Summary
- Architecture: Frozen Wav2Vec2 (
facebook/wav2vec2-xls-r-300m, layer 14) + AASIST Graph Neural Network backend - Sampling Rate: 16 kHz mono Float32 PCM
- Telephony Robustness: Trained with simulated acoustic impairments, handset frequency response, AGC, and noise suppression filters (
modern_phoneseries) - Calibration: Multi-signal isotonic & logistic fusion (
chunk_clean/chunk_fused_telephony) combining acoustic artifact detection with prosody dynamics
Checkpoints Included
modern_phone/best.pt: Top-performing telephony checkpoint (Epoch 23, Validation EER 0.48% / 99.5% accuracy)modern_phone/last.pt: Final training checkpoint with optimization historycodec_augmented/best.pt: Baseline wideband codec-augmented checkpointcalibrators/chunk_clean.joblib: Clean in-domain calibrated logistic regressorcalibrators/chunk_fused_telephony.joblib: Multi-signal fusion calibratorsignals/prosody.joblib: Secondary pitch/energy forensic scorer
Quick Setup for Team Members
Clone the repository and pull the models in one command:
git clone https://github.com/xOAviOx/kavach.git
cd kavach
uv sync
uv run python scripts/download_from_hf.py
Run serving:
uv run uvicorn kavach.serving.app:app --host 0.0.0.0 --port 8100