Downloads · 30 days
10
29% of all-time downloads
KomdigiITS-86M-DFK-DeepfakeAudioClassification
aitf-komdigi/KomdigiITS-86M-DFK-DeepfakeAudioClassification
KomdigiITS-86M-DFK-DeepfakeAudioClassification is a audio classification model from aitf-komdigi. 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 apache-2.0.
Model fine-tuned dari MIT/ast-finetuned-audioset-10-10-0.4593 untuk deteksi audio deepfake.
All-time downloads
35
Public
Parameters
86.2M
690 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors345 MB · 100%
At a glance
- Task
- Audio Classification
- License
- apache-2.0
- Model type
- audio-spectrogram-transformer
- Access
- Public
- Created
- Jun 3, 2026
- Updated
- Jun 3, 2026
- SHA
- 415b2613
Base models
Model card
From the Hugging Face model README
AITF Audio Deepfake Detection AST — Fine-tuned Model
Model fine-tuned dari MIT/ast-finetuned-audioset-10-10-0.4593 untuk deteksi audio deepfake.
Label
| Label | Keterangan |
|---|---|
| Real | Audio asli yang dibuat oleh manusia |
| Fake | Audio sintetis atau hasil generative AI |
Training Info
Base model : MIT/ast-finetuned-audioset-10-10-0.4593
Architecture : Audio Spectrogram Transformer (AST)
Task : Binary Audio Deepfake Detection
Framework : PyTorch + Hugging Face Transformers
Input : Audio mono 16 kHz
Output : Single-logit binary classification
Loss Function : BCEWithLogitsLoss
Classifier Head : Linear(768 → 1)
- Task
- Audio Classification
- Type
- audio-spectrogram-transformer
- License
- apache-2.0
- Languages
- id
- Created
- Jun 3, 2026
- Updated
- Jun 3, 2026