update model-card

README.md

@@ -48,7 +48,7 @@ import pyonmttok
 from huggingface_hub import snapshot_download
 model_dir = snapshot_download(repo_id="projecte-aina/mt-aina-it-ca", revision="main")
 tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = model_dir + "/spm.model")
-tokenized=tokenizer.tokenize("Benvingut al projecte Aina!")
+tokenized=tokenizer.tokenize("Benvenuto al progetto Aina!")
 translator = ctranslate2.Translator(model_dir)
 translated = translator.translate_batch([tokenized[0]])
 print(tokenizer.detokenize(translated[0][0]['tokens']))
@@ -117,9 +117,9 @@ We use the BLEU score for evaluation on the Flores test set: [Flores-101](https:
 Below are the evaluation results on the machine translation from Catalan to Italian compared to [Softcatalà](https://www.softcatala.org/) and [Google Translate](https://translate.google.es/?hl=es):
 | Test set         	| SoftCatalà | Google Translate |mt-aina-it-ca|
 |----------------------|------------|------------------|---------------|
-| Flores 101 dev   	| 25,4     	| **30,4**     	| 27,4     	|
-| Flores 101 devtest   |26,6   	| **31,2**     	| 27,9     	|
-| Average          	| 26,0   	| **30,8**     	| 27,7      	|
+| Flores 101 dev   	| 25,4     	| **30,4**     	| 26,6     	|
+| Flores 101 devtest   |26,6   	| **31,2**     	| 27,2     	|
+| Average          	| 26,0   	| **30,8**     	| 29,6      	|
 ## Additional information
 ### Author
 Language Technologies Unit (LangTech) at the Barcelona Supercomputing Center (langtech@bsc.es)