Update README.md

README.md

@@ -13,9 +13,10 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# byt5-finetuned-indocollex-informal-to-formal
+# ByT5 Finetuned IndoCollex Informal to Formal with Word Formation Tag
+
+This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on [IndoCollex dataset](https://github.com/haryoa/indo-collex) on informal-formal transformation.
 
-This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.1665
 - Cer: 0.1952
@@ -23,9 +24,16 @@ It achieves the following results on the evaluation set:
 - Word Acc: 0.519
 - Gen Len: 7.6914
 
+On test set, it achieves following results :
+- CER: 0.2152
+- WER: 0.5125
+- Word Accuracy: 0.4875
+
 ## Model description
 
-More information needed
+Inputs are constructed like this `tag transformasi kata: %s. kata: %s`
+
+For example : `tag transformasi kata: sound-alter. kata: sampe`
 
 ## Intended uses & limitations