Saltar al contenido
ModelPublicadoExterno
Descargar

DF Arena 500M V 1

We are excited to release DF Arena 500M Universal Antispoofing model 🔥trained on traditional speech antispoofing datasets in addition to singing and environmental deepfake data. Check out the release on DF Arena...

Fuentehuggingface.co/Speech-Arena-2025/DF_Arena_500M_V_1/tree/8258fa8e74ff9b8ad20d4c939c1a7f694a6e4080
TipoOtherVersiónRevision 8258fa8Bcalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
1,63 GB
Versión
vRevision 8258fa8
Actualizado
22 sept 2026
Descargas
2,5 mil
Fuente
Hugging Face

Descripción de la fuente

DF Arena 500M - Antispoofing Model

We are excited to release DF Arena 500M Universal Antispoofing model 🔥trained on traditional speech antispoofing datasets in addition to singing and environmental deepfake data. Check out the release on DF Arena leaderboard

Training Data

  • ASVspoof 2019, 2024
  • Codecfake
  • LibriSeVoc
  • DFADD
  • CTRSVDD
  • SpoofCeleb
  • MLAAD
  • EnvSDD

Usage

from transformers import pipeline
import librosa

 #load model
pipe = pipeline("antispoofing", model="Speech-Arena-2025/DF_Arena_500M_V_1", trust_remote_code=True, device='cuda')
audio, sr = librosa.load("sample.wav", sr=16000)
result = pipe(audio)
print(result)
# Output: 
{'label': 'spoof', 'logits': [[1.5515458583831787, -1.2254822254180908]], 'score': 0.9414217472076416, 'all_scores': {'spoof': 0.9414217472076416, 'bonafide': 0.05857823044061661}}

Evaluation

Evaluation

DatasetEER (%)F1-scoreAccuracy (%)
dfadd0.000.999399.97
add_2023_round_212.300.913387.70
codecfake6.360.899793.65
asvspoof_2021_la4.230.819195.77
in_the_wild1.760.986098.24
asvspoof_20191.090.949498.91
add_2022_track_123.980.645376.02
fake_or_real2.300.977397.73
asvspoof_202412.390.742387.61
add_2022_track_32.770.920097.23
add_2023_round_17.470.946592.53
librisevoc0.120.995599.87
asvspoof_2021_df3.300.620096.70
sonar1.900.983798.13
Average5.780.88494.19
Pooled10.880.7889.11

License

We use a non-commercial license which can be found here

Contact

For questions or issues, please open an issue on the model repository or contact us at [email protected].

Stay tuned for upcoming versions of our models!

Citation

If you use this model in your work, it can be cited as :

@misc{kulkarni2026compactsslbackbonesmatter,
      title={Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR}, 
      author={Ajinkya Kulkarni and Sandipana Dowerah and Atharva Kulkarni and Tanel Alumäe and Mathew Magimai Doss},
      year={2026},
      eprint={2603.06164},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2603.06164}, 
}

Fuentes

1 fuente
Hugging FacePrincipalVersión 8258fa8e74ff9b8ad20d4c939c1a7f694a6e4080
huggingface.co/Speech-Arena-2025/DF_Arena_500M_V_1/tree/8258fa8e74ff9b8ad20d4c939c1a7f694a6e4080

Verificado 6 sept

Artefactos del modelo

1 artefacto

pytorch_model.bin

bin · 1,63 GB · SHA-256 ebd7662047f3…66a2 · Hugging Face

Descargar

Extractos de fuentes

2 extractos
Readme6 septhuggingface.co/Speech-Arena-2025/DF_Arena_500M_V_1

--- language: - en tags: - audio - audio-classification - antispoofing - deepfake-detection - speech license: other pipeline_tag: audio-classification --- # DF Arena 500M - Antispoofing Model We are excited to release DF Arena 500M Universal Antispoofing model 🔥trained on traditional speech antispoofing datasets in addition to singing and environmental deepfake data. Check out the release on [DF Arena leaderboard](https://huggingface.co/spaces/Speech-Arena-2025/Speech-DF-Arena) # Training Data - **ASVspoof 2019, 2024** - **Codecfake** - **LibriSeVoc** - **DFADD** - **CTRSVDD** - **SpoofCeleb** - **MLAAD** - **EnvSDD** ## Usage ```python from transformers import pipeline import librosa #load model pipe = pipeline("antispoofing", model="Speech-Arena-2025/DF_Arena_500M_V_1", trust_remote_code=True, device='cuda') audio, sr = librosa.load("sample.wav", sr=16000) result = pipe(audio) print(result) # Output: {'label': 'spoof', 'logits': [[1.5515458583831787, -1.2254822254180908]], 'score': 0.9414217472076416, 'all_scores': {'spoof': 0.9414217472076416, 'bonafide': 0.05857823044061661}} ``` # Evaluation # Evaluation | Dataset | EER (%) | F1-score | Accuracy (%) | |----------------------|----------|-----------|---------------| | dfadd | 0.00 | 0.9993 | 99.97 | | add_2023_round_2 | 12.30 | 0.9133 | 87.70 | | codecfake | 6.36 | 0.8997 | 93.65 | | asvspoof_2021_la | 4.23 | 0.8191 | 95.77 | | in_the_wild | 1.76 | 0.9860 | 98.24 | | asvspoof_2019 | 1.09 | 0.9494 | 98.91 | | add_2022_track_1 | 23.98 | 0.6453 | 76.02 | | fake_or_real | 2.30 | 0.9773 | 97.73 | | asvspoof_2024 | 12.39 | 0.7423 | 87.61 | | add_2022_track_3 | 2.77 | 0.9200 | 97.23 | | add_2023_round_1 | 7.47 | 0.9465 | 92.53 | | librisevoc | 0.12 | 0.9955 | 99.87 | | asvspoof_2021_df | 3.30 | 0.6200 | 96.70 | | sonar | 1.90 | 0.9837 | 98.13 | | **Average** | **5.78** | **0.884**| **94.19** | | **Pooled** | **10.88** | **0.78** | **89.11** | ## License We use a non-commercial license which can be found [here](./LICENSE.txt) ## Contact For questions or issues, please open an issue on the model repository or contact us at [email protected]. Stay tuned for upcoming versions of our models! ## Citation If you use this model in your work, it can be cited as : ```bibtex @misc{kulkarni2026compactsslbackbonesmatter, title={Do Compact SSL Backbones Matter for Audio Deepfake Detection? A C...

Note6 septhuggingface.co/Speech-Arena-2025/DF_Arena_500M_V_1

Source context: 2507 downloads · 1 likes · Pipeline audio-classification · Repo Speech-Arena-2025/DF_Arena_500M_V_1