Update README.md

README.md

@@ -25,7 +25,7 @@ It also runs very fast on CPU too!
 
 Use cases could be for ASR tasks (some models give text without casing and punctuation, like on auto-generated subtitles for YouTube videos from 2023/2024/2025)
 ## Limitations
-This model was trained ONLY on English Tatoeba data and doesn't do well for other languages.
+This model was trained ONLY on English Tatoeba data (from 21 Feburary 2026) and doesn't do well for other languages.
 
 Also, it doesn't do perfectly sometimes (especially with proper nouns like "Minecraft").