Spectra-AASIST3 — a speech anti-spoofing model pairing a wav2vec 2.0 (XLS-R-300m) self-supervised front-end with a KAN-enhanced AASIST (KAN-AASIST) back-end. The model takes a raw speech waveform and returns a score where higher = more bona fide.
lab260/Spectra-AASIST3
(model.safetensors, self-contained — bundles the SSL encoder weights)The exact wrapper that produced the Arena scores is in
spectra_aasist3.py; the vendored network is
spectra_aasist3_net.py (copied from the source model.py).
transformers Wav2Vec2Model
(facebook/wav2vec2-xls-r-300m), producing 1024-d frame features (the base arch is
fetched at init, then every weight is overwritten by the checkpoint).Linear(1024 → 128) projection (SELU, dropout 0.1).expected_sample_rate = 16000).batch_size = 24 (throughput plateaus ~50 utt/s for bs ≥ 16 on an RTX 4070 Ti SUPER).Evaluated through the reproducible
Speech Anti-Spoofing Arena.
Each result is sha-pinned and reproducible from the score file via
speech-spoof-bench reproduce --scoring.
| Dataset | Split | EER % | Trials | Skipped | Notes |
|---|---|---|---|---|---|
| CD-ADD | test | 0.00 | 20,786 | 0 | modern neural-TTS deepfake |
| SONAR | test | 0.44 | 3,948 | 0 | multilingual real-world deepfake |
| CVoiceFake_small | test | 0.51 | 138,136 | 0 | multilingual TTS/vocoder deepfake |
| CFAD | test | 0.71 | 62,999 | 0 | Chinese fake-audio detection |
| LibriSeVoc | test | 0.83 | 18,487 | 0 | vocoder-based deepfake |
| ASVspoof2019_LA | test | 0.97 | 71,237 | 0 | in-domain family |
| InTheWild | test | 1.20 | 31,779 | 0 | out-of-domain (real-world) |
| ASVspoof2021_DF | test | 4.30 | 611,829 | 0 | cross-dataset (deepfake) |
| ASVspoof2021_LA | test | 4.38 | 181,566 | 0 | cross-dataset (logical access) |
| ASVspoof5 | test | 15.09 | 680,774 | 0 | adversarial / hardest set |
The wrapper loads weights from the Hub via PyTorchModelHubMixin:
import numpy as np
from spectra_aasist3 import SpectraAASIST3 # spectra_aasist3.py + spectra_aasist3_net.py
m = SpectraAASIST3()
m.load() # from_pretrained("lab260/Spectra-AASIST3")
audio = np.random.randn(48000).astype(np.float32) # float32 mono 16 kHz
print(m.score_batch([audio], [16000])[0]) # higher = more bona fide
m.unload()
Internally the wrapper applies preemphasis, windows to 64,600 samples, runs the
network, and returns logits[:, 1] (class 1 = bona fide). spectra_aasist3.py
is the exact speech_spoof_bench model that produced the Arena scores.txt.
Apache-2.0 — see the source repository.
spectra-aasist3.onnx 1.3 GBmodel.safetensors 1.3 GB