Upload folder using huggingface_hub
Browse files- README.md +23 -0
- best_audio_model.pth.tar +3 -0
- best_model.pth.tar +3 -0
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# AI vs Real Content Detector
|
| 3 |
+
|
| 4 |
+
This repository contains models for detecting AI-generated content:
|
| 5 |
+
|
| 6 |
+
## Models
|
| 7 |
+
|
| 8 |
+
1. **Audio Model** (best_audio_model.pth.tar)
|
| 9 |
+
- Validation Accuracy: 98.55%
|
| 10 |
+
- Last Updated: 2025-01-31T09:51:03.853278
|
| 11 |
+
|
| 12 |
+
2. **Image Model** (best_model.pth.tar)
|
| 13 |
+
- Uses DINOv2 + ResNet feature fusion
|
| 14 |
+
- Enhanced with attention mechanism
|
| 15 |
+
|
| 16 |
+
## Architecture
|
| 17 |
+
- Feature Fusion Attention mechanism
|
| 18 |
+
- DINOv2 + ResNet50 backbone
|
| 19 |
+
- Custom classifier head
|
| 20 |
+
|
| 21 |
+
## Usage
|
| 22 |
+
Check the repository for inference code examples.
|
| 23 |
+
|
best_audio_model.pth.tar
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4936eb460f9ec01c18d7e92b036b5a30b31534eb6c8774dd3993731fe82ca6fd
|
| 3 |
+
size 34659322
|
best_model.pth.tar
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a4cd6309c66b6e31007f02586830f2ccf0232c67c222cccc851426617fc6191
|
| 3 |
+
size 34658898
|