Update README.md
Browse files
README.md
CHANGED
|
@@ -39,6 +39,8 @@ inference:
|
|
| 39 |
/>
|
| 40 |
</p>
|
| 41 |
|
|
|
|
|
|
|
| 42 |
## Overview
|
| 43 |
|
| 44 |
> This is the future iteration of [AIRealNet](https://huggingface.co/Modotte/AIRealNet)
|
|
@@ -54,8 +56,6 @@ A key design choice addresses a common failure mode of public deepfake detectors
|
|
| 54 |
|
| 55 |
**Default decision threshold**: 0.5 (tune per use-case).
|
| 56 |
|
| 57 |
-
[Click Here for Inference](https://huggingface.co/spaces/sujalrajpoot/AIRealNetAudio)
|
| 58 |
-
|
| 59 |
## Architecture
|
| 60 |
|
| 61 |
This is a **Wav2Vec-based audio encoder** operating at **16 kHz**, paired with a projection layer that maps its base features of dimension **768** (pooled from shape `[T, 768]`) down to **256**. This 256-dimensional representation is the expected input shape for the classification head, which is a **single-layer MLP** producing 2 output logits (with softmax applied during inference).
|
|
|
|
| 39 |
/>
|
| 40 |
</p>
|
| 41 |
|
| 42 |
+
- [Live Demo](https://huggingface.co/spaces/sujalrajpoot/AIRealNetAudio)
|
| 43 |
+
|
| 44 |
## Overview
|
| 45 |
|
| 46 |
> This is the future iteration of [AIRealNet](https://huggingface.co/Modotte/AIRealNet)
|
|
|
|
| 56 |
|
| 57 |
**Default decision threshold**: 0.5 (tune per use-case).
|
| 58 |
|
|
|
|
|
|
|
| 59 |
## Architecture
|
| 60 |
|
| 61 |
This is a **Wav2Vec-based audio encoder** operating at **16 kHz**, paired with a projection layer that maps its base features of dimension **768** (pooled from shape `[T, 768]`) down to **256**. This 256-dimensional representation is the expected input shape for the classification head, which is a **single-layer MLP** producing 2 output logits (with softmax applied during inference).
|