Update README.md

README.md

@@ -54,7 +54,7 @@ This model is a binary classification head fine-tuned version of [MIT/ast-finetu
 - **Base Model**: MIT/ast-finetuned-audioset-10-10-0.4593 (AST pretrained on AudioSet)
 - **Task**: Binary classification (fake/real audio detection)
 - **Input**: Audio converted to Mel spectrogram (128 mel bins, 1024 time frames)
-- **Output**: Binary prediction (0: real audio, 1: fake audio)
+- **Output**: Probabilities [fake_prob, real_prob]
 - **Training Hardware**: 2x NVIDIA T4 GPUs
 
 ## Training Configuration