Update the model card

README.md

@@ -5,17 +5,17 @@ license: cc-by-nc-4.0
 # BLASER 2.0
 [[Paper]]()
 
-BLASER 2.0 is the new version of BLASER [Chen et al., 2023](https://aclanthology.org/2023.acl-long.504/),
-a model for automatic evaluation of machine translation quality.
+BLASER 2.0 is the new version of BLASER ([Chen et al., 2023](https://aclanthology.org/2023.acl-long.504/)),
+a family of models for automatic evaluation of machine translation quality.
 
 BLASER 2.0 is based on [SONAR](https://huggingface.co/facebook/SONAR) sentence embeddings 
 and works with both speech and text modalities. 
 
-The actual model predicts a similarity score for the translation based on the source sentence 
-and the reference translation. Its sibling model, [BLASER 2.0-QE](facebook/blaser-2.0-qe),
-does not use references.
+The actual model predicts a similarity score for the translated sentence based on the the translation, 
+the source sentence, and the reference translation. 
+Its sibling model, [BLASER 2.0 QE](https://huggingface.co/facebook/blaser-2.0-qe), does not use references.
 
-Supervised BLASER model are trained to predict cross-lingual semantic similarity scores, 
+Supervised BLASER models are trained to predict cross-lingual semantic similarity scores, 
 XSTS ([Licht et al., 2022](https://aclanthology.org/2022.amta-research.24/)), 
 on a scale where 1 corresponds to completely unrelated sentences and 
 5 corresponds to fully semantically equivalent sentences.