Update README.md

README.md

@@ -28,11 +28,11 @@ During early experiments, we observed that Whisper Tiny often produced invalid o
 
 The training loss combined the standard ASR loss with KD loss:
 
-\[
-L_{t} = \lambda_{lm} \, \text{CE}(\text{asr}, \text{true token}) + (1 - \lambda_{lm}) \, \text{KLD}(\text{asr distribution}, \text{mlm prediction})
-\]
+$$
+L_t = \lambda_{lm} \, \text{CE}(\text{asr}, \text{true token}) + (1 - \lambda_{lm}) \, \text{KLD}(\text{asr distribution}, \text{mlm prediction})
+$$
 
-where \(\lambda_{lm}\) balances the two components.
+where $\lambda_{lm}$ balances the two components.
 
 ### Hyperparameters