Downloads · 30 days
0
deepfake-audio-stage1-aasist
Naveedr/deepfake-audio-stage1-aasist
deepfake-audio-stage1-aasist is a audio classification model from Naveedr. Use it for the audio classification task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Architecture: AASIST (graph-attention anti-spoofing network), from-scratch trained (not XLS-R backed). Base weights: official ASVspoof2019 LA pretrained checkpoint from https://github.com/clovaai/aasist, [fine-tuned o…
Access
Public
Updated Jul 16, 2026
Repo size
2.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth2.6 MB · 99%
At a glance
- Task
- Audio Classification
- License
- other
- Access
- Public
- Created
- Jul 15, 2026
- Updated
- Jul 16, 2026
- SHA
- 7c210614
Model card
From the Hugging Face model README
Stage 1 -- AASIST Audio Deepfake Detector
Architecture: AASIST (graph-attention anti-spoofing network), from-scratch trained (not XLS-R backed). Base weights: official ASVspoof2019 LA pretrained checkpoint from https://github.com/clovaai/aasist, [fine-tuned on: DESCRIBE YOUR DATA HERE].
Known limitations:
- Fine-tuned primarily on English ASVspoof-style data; cross-lingual/accented performance not validated.
- Sensitive to codec compression (Opus/AMR/MP3) unless explicitly augmented for it.
- Expects 16kHz mono input, fixed 64600-sample (~4s) window via repeat-padding.
Label convention: 0 = spoof, 1 = bonafide (verify against a known sample before trusting in production).
Eval: EER = [FILL IN] % on [FILL IN dataset].
- Task
- Audio Classification
- License
- other
- Created
- Jul 15, 2026
- Updated
- Jul 16, 2026