Update README.md

README.md

@@ -20,7 +20,10 @@ library_name: fairseq
 
 HUTTER-12: H(uBERT) UTTER model covering 12 languages.
 
-* Total training hours: 1,622 (fr: 300; es: 300; pt: 102.3; da: 3.5; de: 300; nl: 72.1; fy: 41.2; zh-CN: 104.6; ja: 37; ar: 61; sw: 300; gn: 0.4)
+* Total training hours: 1,622 from:
+Romance= {fr: 300; es: 300; pt: 102.3};
+West-Germanic={da: 3.5; de: 300; nl: 72.1; fy: 41.2;};
+Unrelated={zh-CN: 104.6; ja: 37; ar: 61; sw: 300; gn: 0.4}
 * Number of updates: 400k
 * Number of iterations: 3
 * Clustering approach: mini-batch K-means (100% of the data)