Update README.md

README.md

@@ -16,7 +16,8 @@ license: cc-by-4.0
 
 Our demo is available [here](https://huggingface.co/spaces/pyf98/OWSM_v3_demo).
 
-OWSM v3.1 is an improved version of OWSM v3. We do not include any new training data. Instead, we utilize a state-of-the-art speech encoder, [E-Branchformer](https://arxiv.org/abs/2210.00077). OWSM v3.1 has 1.02B parameters in total and is trained on 180k hours of public speech data. It significantly outperforms OWSM v3 in almost all evaluation benchmarks.
+**OWSM v3.1 is an improved version of OWSM v3. It significantly outperforms OWSM v3 in almost all evaluation benchmarks.**
+We do not include any new training data. Instead, we utilize a state-of-the-art speech encoder, [E-Branchformer](https://arxiv.org/abs/2210.00077). OWSM v3.1 has 1.02B parameters in total and is trained on 180k hours of public speech data.
 
 Specifically, it supports the following speech-to-text tasks:
 - Speech recognition