Download implementation-notes.md from SpeechAntiSpoofingBenchmarks/Nes2Net-X-CtrSVDD: direct link, hf CLI and curl.
- Browser
- Download file 4.39 kB
-
https://huggingface.co/SpeechAntiSpoofingBenchmarks/Nes2Net-X-CtrSVDD/resolve/main/implementation-notes.md
- Command line
-
hf download hf://SpeechAntiSpoofingBenchmarks/Nes2Net-X-CtrSVDD/implementation-notes.md
-
curl -L -o implementation-notes.md https://huggingface.co/SpeechAntiSpoofingBenchmarks/Nes2Net-X-CtrSVDD/resolve/main/implementation-notes.md
Nes2Net-X-CtrSVDD β implementation notes
Plan: speech-spoof-bench/docs/plans/2026-11-07-eleven-model-batch-arena-submission.md (model #11).
Singing-voice deepfake detector (CtrSVDD / SVDD 2024); the speech Nes2Net is the separate benchmarks/Nes2Net/ row.
Source
- Code: github Liu-Tianchi/Nes2Net @
3fed08a603991cf8b422978e0c942a976deb9399(Apache-2.0),models/WavLM_Nes2Net_X.pyclassWavLM_Nes2Net_noRes_w_allT;eval.sh:--agg SEA --pool_func mean --dilation 1 --Nes_ratio 8 8 --SE_ratio 1;eval.py(full utterance, bs 1,model.eval(), filtered non-strict load). - Weights: HF nielsr/nes2net-checkpoints @
06818cabb70c44d3008fdeb9285f141f198aa92a,WavLM_Nes2Net_X_e75_seed420_valid0.03192785031473534.pt(1,264,329,467 B, sha256f1c2942635c68b584a742b10dbc5630759fc6cd55409ff8dc4d71f9c81ccdf5f) β an HF mirror (by nielsr) of the authors' Google-Drive release (README row WavLM_Nes2Net_X seed 420 epoch 75). No license β not re-hosted, linked; local symlink intobenchmarks/_ckpt_dl/nielsr__nes2net-checkpoints/. - Front-end config:
cfgof s3prl/converted_ckpts @8cad0b370e7e35f8d56951d95d2be036ea85510cwavlm_large.pt(sha2566fb4b3c3β¦100f, read with weights_only=True) βwavlm_large_cfg.json.normalize: true.
Port (_net.py)
- s3prl 0.4.18
WavLM/WavLMConfig(installed package) built from the vendored cfg; no base weights or hub download._UpstreamExpertstands in for s3prl's UpstreamExpert (keepsssl_model.model.model.*keys): per-clipF.layer_norm(wav, (L,)),extract_features(mask=False), 25 hidden states via forward pre-hooks on the 24 encoder layers (= s3prl hookinput[0].transpose(0,1)) + forward hook on the encoder (output[0], after the final LayerNorm). padding_mask=None (s3prl passes all-False for equal lengths; identical, see parity).int(shape)in layer_norm keeps the ONNX trace static. - SEA merge (AdaptiveAvgPool2d β Linear 25β8 β ReLU β Linear 8β25 β Sigmoid β weighted sum) and the Nes2Net-X back-end verbatim; fc Linear(1024,1). Training-only branches (AttM/WeightedSum/ASTP, SSL_freeze) dropped.
- Checkpoint: plain OrderedDict, 1050 tensors (488 WavLM),
torch.load(weights_only=True),strict=True0 missing / 0 unexpected (the authors' filtered load also drops/misses nothing). - Score = the logit (focal-BCE training, label 1 = bonafide); higher = bona fide.
- Params 315,964,534 (WavLM-Large 315,453,120 + SEA 400 + back-end 511,014).
Input (maintainer: 4 s cap)
Authors evaluate the full utterance (their 4s mode = first 64000, repeat-padded). Here first 64600 samples
(Arena rule), tile-repeat if shorter, empty β zeros. FP32, cuDNN TF32 off.
Source parity (source_parity.py, log source_parity.log)
Authors' WavLM_Nes2Net_X.py with hub.wavlm_large patched to s3prl wavlm_local(<local wavlm_large.pt>) (real
UpstreamExpert with hooks + all-False padding mask), authors' filtered load, vs our wrapper on 24 In-the-Wild clips
(same window): max |Ξ| = 0 single-clip, 3.1e-6 batched.
Batch sweep (sweep.py, 2026-11-07, logs logs_sweep_g{2,1}.txt)
| card | best | notes |
|---|---|---|
| RTX 4070 Ti SUPER (idx 2) | 114.6 utt/s @24 | plateau 16β64 β batch_size = 24 |
| RTX 5060 Ti (idx 1) | 43.7 utt/s @4 | ~31 at bs β₯ 8 β 4 on 5060 |
Sanity (PyTorch)
Full J-SPAW_LA (results_pt/, RTX 5060 Ti idx 3): EER 1.440 % (2397 trials, 0 skipped) β surprisingly strong
for a singing model; not inverted. Copied to results/J-SPAW_LA. Unit tests test_nes2net_x_ctrsvdd.py: 8 passed.
TensorRT (trt_nes2net_x_ctrsvdd.py, sidecar trt_nes2net-x-ctrsvdd.json, TRT 10.16.1.11)
FP16 produces NaN (WavLM overflow; build Spearman 0.40) β FP32 on both cards; FP16 engines deleted.
| card | precision | best batch | utt/s (sweep) | build parity Spearman / max Ξ | J-SPAW EER | J-SPAW Spearman vs PT / max Ξ |
|---|---|---|---|---|---|---|
| RTX 4070 Ti SUPER (idx 2) | FP32 | 32 | 167.1 | 1.00000 / 0.0027 | 1.4402 (=PT) | 1.000000 / 0.0053 |
| RTX 5060 Ti (idx 3) | FP32 | 32 | 113.3 | 1.00000 / 0.022 | 1.4402 (=PT) | 0.999999 / 0.013 |
Scripts: run_sweep.sh, run_pt.sh [gpu], run_trt_export.sh ["3 2"], run_trt_jspaw.sh <gpu>, cmp_scores.py.
meta.yaml
trained_on omitted (CtrSVDD only). Self-reported CtrSVDD test EER 2.48 % (2.22 % w/ ACESinger bona fide).