Update README.md

README.md

@@ -14,10 +14,12 @@ datasets:
 ---
 ## xm_transformer_unity_en-hk
 
-Speech-to-speech translation model from fairseq:
+Speech-to-speech translation model with two-pass decoder (UnitY) from fairseq:
 - English-Hokkien
-- Trained on MuST-C
+- Trained with supervised data in TED domain, and weakly supervised data in TED and Audiobook domain. See [here]( https://research.facebook.com/publications/hokkien-direct-speech-to-speech-translation) 
+for training details.
 - Speech synthesis with [facebook/unit_hifigan_HK_layer12.km2500_frame_TAT-TTS](https://huggingface.co/facebook/unit_hifigan_HK_layer12.km2500_frame_TAT-TTS)
+- [Examples](https://github.com/facebookresearch/fairseq/tree/ust/examples/hokkien)
 
 ## Usage
 ```python