Update README.md

README.md

@@ -53,7 +53,11 @@ This model is fine-tuned from [microsoft/Phi-4-multimodal-instruct](https://hugg
 
 This model is trained 960 steps on datasets for Korean Audio Speech Recognition on H100.
 
-After that, we continue training with [CoVoST2 Dataset](https://huggingface.co/datasets/junnei/covost2) / [Only for Korean](https://huggingface.co/datasets/junnei/covost2-ko) for AST.
+After that, we continue training with [CoVoST2 Dataset][Covost2] / [CoVoST2-Ko][Covost2-ko] for AST.
+
+[Covost2]: https://huggingface.co/datasets/junnei/covost2
+[Covost2-ko]: https://huggingface.co/datasets/junnei/covost2-ko
+[ASR]: https://huggingface.co/junnei/Phi-4-multimodal-instruct-ko-asr
 
 ## Evaluation
 
@@ -74,5 +78,3 @@ Compared to [Phi-4-mm-inst-zeroth-kor](https://huggingface.co/seastar105/Phi-4-m
 | + 1 epoch finetune with [Covost-Ko][Covost2-ko]|  3.88       |     -      |   **8.07**   |     **10.09**    |   **18.82**  |    **15.41**     |
 | **AST finetuned model(this model)**            |  **1.77**   |  **2.99**  |   **8.01**   |     **9.09**     |   **17.09**  |    **11.82**     | 
 
-[Covost2-ko]: https://huggingface.co/datasets/junnei/covost2-ko
-[ASR]: https://huggingface.co/junnei/Phi-4-multimodal-instruct-ko-asr