Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,14 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
A deep learning model for audio classification, designed to detect AI-generated music.
|
| 5 |
+
|
| 6 |
+
Model: EfficientNetB0 (Transfer Learning)
|
| 7 |
+
|
| 8 |
+
Framework: TensorFlow / Keras
|
| 9 |
+
|
| 10 |
+
Task: Binary Classification (AI Music vs. Real Music)
|
| 11 |
+
|
| 12 |
+
Input: Mel Spectrograms (224x224) generated from audio files.
|
| 13 |
+
|
| 14 |
+
Training Data: Trained on a balanced dataset of thousands of modern songs from sources like the Free Music Archive, NCS, and the Suno AI dataset on Kaggle, all standardized to a consistent bitrate.
|