Update README.md

README.md

@@ -22,11 +22,10 @@ This model was fine-tuned on over 24 hours of transcribed upper sorbian speech t
 ## Training Details
 - **Hyperparameters**: 
   - Batch size: 64
-  - Learning rate: 3e-6
-  - Linear Decay
+  - Learning rate: 3e-6, linear decay
 - **Optimizer**: AdamW
-- **Warmup**: 1000 Steps
-- **Additional Techniques**: BF16 Training, Frozen initial 15 layers
+- **Warmup**: 1000 steps
+- **Additional Techniques**: BF16 training, initial 15 layers frozen
 
 
 ## Performance