MMS 1B AntiDeepfake
Bit-exact copy of nii-yamagishilab/mms-1b-anti-deepfake (the AntiDeepfake collection, nii-yamagishilab), hosted for the Speech Anti-Spoofing Arena. Trained with RawBoost data augmentation (default).
Source du modèle
- Type
- Other
- Taille du fichier
- 1,81 MB–3,60 GB
- Modèle de base
- nii-yamagishilab/mms-1b-anti-deepfake
- Version
- vRevision 5ca454a
- Mis à jour
- 25 oct. 2026
- Téléchargements
- 29
- Source
- Hugging Face
Description de la source
MMS-1B-AntiDeepfake
Bit-exact copy of nii-yamagishilab/mms-1b-anti-deepfake (the AntiDeepfake
collection, nii-yamagishilab), hosted for the Speech Anti-Spoofing Arena.
Trained with RawBoost data augmentation (default).
- Paper: Post-training for Deepfake Speech Detection, arXiv:2506.21090
- Original code: https://github.com/nii-yamagishilab/AntiDeepfake
- Backbone: MMS-1B; head = AdaptiveAvgPool1d + Linear(D, 2). Score = real logit.
- License: CC BY-NC-SA 4.0 (non-commercial) — inherited from the source.
⚠️ Evaluation restriction
It is STRICTLY PROHIBITED to evaluate this model on its training / in-domain corpora: ASVspoof2019 LA, ASVspoof2021 LA/DF, ASVspoof5, CFAD, DECRO, DFADD, "Diffuse or Confuse", DiffSSD, DSD, HABLA, MLAAD, SpoofCeleb, CVoiceFake, any LibriTTS-based set (incl. SONAR, CD-ADD, LibriSeVoc), any VoxCeleb-based set, WaveFake, any FLEURS-based set, CodecFake (any variant), any AIShell3-based set, and any MLS-based set. On the Arena it is evaluated only on ArAD and In-the-Wild.
All credit to the original authors (Ge, Wang, et al., NII).
Arena results
EER% 0.49 on XMAD EER% 0.60 on PyAra EER% 6.90 on ODSS EER% 0.06 on J-SPAW_LA EER% 3.84 on DeepVoice EER% 3.30 on InTheWild EER% 4.34 on ArAD 1-SRR% 1.72 on LRLspoof EER% 0.54 on EmoFake_test 1-SRR% 13.97 on EmoSpoofTTS arena tier arena rank
Maintainer
Maintained by Kirill Borodin (SpeechAntiSpoofingBenchmarks).
- Email: [email protected]
- Telegram: @korallll_ai
Sources
1 source
Sources
1 sourceVérifié 25 oct.
Download files
Artefacts du modèle
2 artefacts
Artefacts du modèle
2 artefactsExtraits de sources
3 extraits
Extraits de sources
3 extraits--- license: cc-by-nc-sa-4.0 base_model: - nii-yamagishilab/mms-1b-anti-deepfake tags: - anti-spoofing - audio-deepfake-detection - speech pipeline_tag: audio-classification --- # MMS-1B-AntiDeepfake Bit-exact copy of [`nii-yamagishilab/mms-1b-anti-deepfake`](https://huggingface.co/nii-yamagishilab/mms-1b-anti-deepfake) (the AntiDeepfake collection, nii-yamagishilab), hosted for the Speech Anti-Spoofing **Arena**. Trained with RawBoost data augmentation (default). - **Paper:** Post-training for Deepfake Speech Detection, [arXiv:2506.21090](https://arxiv.org/abs/2506.21090) - **Original code:** https://github.com/nii-yamagishilab/AntiDeepfake - **Backbone:** MMS-1B; head = AdaptiveAvgPool1d + Linear(D, 2). Score = real logit. - **License:** CC BY-NC-SA 4.0 (non-commercial) — inherited from the source. ## ⚠️ Evaluation restriction It is **STRICTLY PROHIBITED** to evaluate this model on its training / in-domain corpora: ASVspoof2019 LA, ASVspoof2021 LA/DF, ASVspoof5, CFAD, DECRO, DFADD, "Diffuse or Confuse", DiffSSD, DSD, HABLA, MLAAD, SpoofCeleb, CVoiceFake, any LibriTTS-based set (incl. SONAR, CD-ADD, LibriSeVoc), any VoxCeleb-based set, WaveFake, any FLEURS-based set, CodecFake (any variant), any AIShell3-based set, and any MLS-based set. On the Arena it is evaluated **only** on ArAD and In-the-Wild. All credit to the original authors (Ge, Wang, et al., NII). ## Arena results <!-- arena-badges --> [](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=mms-1b-antideepfake) [](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=mms-1b-antideepfake) [](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=mms-1b-antideepfake) [](https://huggingface.co/spaces/SpeechAntiSpoofingBenchmarks/SpeechAntiSpoofingArena?system=mms-1b-antideepfake) [](https://huggingface.co/spaces/SpeechAntiSpoofingBen...
Source context: 29 downloads · 0 likes · Pipeline audio-classification · Repo SpeechAntiSpoofingBenchmarks/MMS-1B-AntiDeepfake
Source context: 9 downloads · 0 likes · Pipeline audio-classification · Repo SpeechAntiSpoofingBenchmarks/MMS-1B-AntiDeepfake
