mahwizzzz commited on
Commit
354a8b7
·
verified ·
1 Parent(s): d5a8846

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -51,7 +51,7 @@ NastaliqBERT uses the NeoBERT architecture with RoPE positional embeddings, SwiG
51
 
52
  ## Why character-level for Urdu?
53
 
54
- Urdu is written in Nastaliq a right-to-left abjad where short vowels are not written. Subword tokenizers fragment Nastaliq ligatures at arbitrary boundaries. Character-level modelling preserves:
55
  - The aspiration digraph ھ (do-chashmi-he) as a distinct unit
56
  - Final letter forms (ے vs ی, ں vs ن)
57
  - Correct morphological boundaries
 
51
 
52
  ## Why character-level for Urdu?
53
 
54
+ Urdu is written in Nastaliq a right-to-left abjad where short vowels are not written. Subword tokenizers fragment Nastaliq ligatures at arbitrary boundaries. Character-level modelling preserves:
55
  - The aspiration digraph ھ (do-chashmi-he) as a distinct unit
56
  - Final letter forms (ے vs ی, ں vs ن)
57
  - Correct morphological boundaries