Update README.md

README.md

@@ -59,6 +59,10 @@ The Catalan-German data collected from the web was a combination of the followin
 | GNOME	|
 | KDE4    	|
 | OpenSubtitles	|
+| MultiParaCrawl |
+| DGT |
+| EUBookshop |
+| NLLB |
 | GlobalVoices|
 | Tatoeba |
 | Books |
@@ -67,17 +71,10 @@ The Catalan-German data collected from the web was a combination of the followin
 
 All corpora except Europarl and Tilde were collected from [Opus](https://opus.nlpl.eu/). 
 The Europarl and Tilde corpora are synthetic parallel corpora created from the original Spanish-German corpora by [SoftCatalà](https://github.com/Softcatala).
+Once all available Catalan-German data had been collected, additional synthetic Catalan data was created from the Spanish side of Spanish-German corpora using [Projecte Aina’s Spanish-Catalan model.](https://huggingface.co/projecte-aina/aina-translator-es-ca)
 
 The synthetic parallel data was created from the following Spanish-German datasets:
 
-| Datasets       	| 
-|-------------------|
-|globalvoices_es-de_20230901	|
-|multiparacrawl_es-de_20230901  |
-|dgt_es-de_20240129           |
-|eubookshop_es-de_20240129    | 
-|nllb_es-de_20240129          |
-|opensubtitles_es-de_20240129 |
 
 
 ### Training procedure