Update README.md

README.md

@@ -3,7 +3,9 @@ tags:
 - espnet
 - audio
 - speech-translation
-language: en
+language:
+- en
+- es
 datasets:
 - cvss
 license: cc-by-4.0
@@ -11,6 +13,8 @@ license: cc-by-4.0
 
 ## ESPnet2 S2ST model
 
+Vocoder is located [here](https://huggingface.co/espnet/cvss-c_en_wavegan_hubert_vocoder), trained by [realzza](https://github.com/realzza)
+
 ### `espnet/jiyang_tang_cvss-c_es-en_discrete_unit`
 
 This model was trained by Jiyang Tang using cvss recipe in [espnet](https://github.com/espnet/espnet/).
@@ -1059,4 +1063,4 @@ or arXiv:
   archivePrefix={arXiv},
   primaryClass={cs.CL}
 }
-```
+```