Update README.md

README.md

@@ -1,3 +1,50 @@
----
-license: mit
----
+---
+license: mit
+datasets:
+- AnodHuang/AMVD_AS
+base_model:
+- MIT/ast-finetuned-audioset-10-10-0.4593
+---
+# AST-AMVD-SAD-v1
+## Description
+A fine-tuned audio classification model for detecting AI-generated audio content.
+## Author
+- Kunyang Huang (huangku@kean.edu)
+- Bin Hu (binhu.philip@gmail.com)
+## Model Details
+### Model Description
+- Architecture: Based on the Audio Spectrogram Transformer (AST) architecture from MIT/ast-finetuned-audioset-10-10-0.4593
+- Input: Audio waveforms converted to mel-spectrogram representations
+- Output: Four-class classification for audio authenticity detection
+### Intended Use
+**This model is designed to:**
+- Detect AI-generated audio content
+- Identify different types of synthetic audio:
+  - Class 0 (H): Real Human Audio
+  - Class 1 (C): AI Cloned Audio
+  - Class 2 (A): AI Generated Audio
+  - Class 3 (Combined): Mixed Human/AI Audio
+- Primary use cases include:
+  - Content authenticity verification
+  - AI-generated content detection systems
+  - Audio forensics applications
+### Training Data
+- Dataset: AMVD_AS Dataset
+- Data Composition:
+  - Balanced samples across four categories
+  - Contains both synthetic and genuine human audio samples
+## Training Procedure
+### Fine-tuning Parameters
+- Base Model: MIT/ast-finetuned-audioset-10-10-0.4593
+- Initial Learning Rate: 4e-5 → 1e-5 (linear decay)	
+- Total Training Steps:	25,000
+- Batch Size: 32
+- Warmup Steps:	5,000
+- Weight Decay: 0.01
+- Gradient Clip Norm: 1.0
+- Training Duration: ~4.5 hours (A100 GPU)
+## Evaluation
+### Validation Performance
+- Training Loss	0.0874
+- Gradient Norm	0.000075778
+- LR Stability	1e-5