Update README.md

README.md

@@ -10,24 +10,29 @@ metrics:
 ---
 # Overview
 ![Scoris logo](https://scoris.lt/logo_smaller.png)
-This is an English-Lithuanian translation model based on [Helsinki-NLP/opus-mt-tc-big-en-lt](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-lt)
-
-For Lithuanian-English translation check another model [scoris-mt-lt-en](https://huggingface.co/scoris/scoris-mt-lt-en)
+This is an English-Lithuanian translation model
 
+Original model: [Helsinki-NLP/opus-mt-tc-big-en-lt](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-lt)
 
 Fine-tuned on large merged data set: [scoris/en-lt-merged-data](https://huggingface.co/datasets/scoris/en-lt-merged-data) (5.4 million sentence pairs)
 
+For Lithuanian-English translation check another model [scoris-mt-lt-en](https://huggingface.co/scoris/scoris-mt-lt-en)
+
+
 Trained on 6 epochs. 
 
 Made by [Scoris](https://scoris.lt) team
 
 # Evaluation:
-Tested on scoris/en-lt-merged-data validation set. Metric: sacrebleu
-
-| model | testset | BLEU  | Gen Len |
-|----------|---------|-------|-------|
-| scoris/scoris-mt-en-lt | scoris/en-lt-merged-data (validation) | 41.8841 	 | 17.4785
-| Helsinki-NLP/opus-mt-tc-big-en-lt | scoris/en-lt-merged-data (validation) | 34.2768 | 17.6664
+Tested on scoris/en-lt-merged-data validation set.
+
+| EN-LT                             | BLEU | ROUGE | chrF/chrF++ |
+|-----------------------------------|------|-------|-------------|
+| scoris/scoris-mt-en-lt            | 41.9 | 0.54  | 0.63        |
+| Helsinki-NLP/opus-mt-tc-big-en-lt | 34.3 | 0.50  | 0.60        |
+| Google Translate                  | 27.1 | 0.48  | 0.60        |
+| Deepl                             | 28.3 | 0.50  | 0.61        |
+_Google and Deepl evaluated using random sample of 1000 sentence pairs._
 
 According to [Google](https://cloud.google.com/translate/automl/docs/evaluate) BLEU score interpretation is following: