Skip to content
Kotoshu Kotoshu 言修

fa فارسی n. — full feature

Persian

Persian with ZWNJ-aware compounds

Specimen

این یک مدسره زیاب است

1. مدسره مدرسه

2. زیاب زیبا

What arrives on demand

dictionary
Hunspell dictionary with full affix morphology and compounding
frequency
No Kelly list under this code; ranking leans on the dictionary and model
semantic
FastText ONNX embedding model for context-aware reranking — available as fluency (~15 MB, the default), full (120 MB), or mini (~3 MB), chosen at setup
keyboard
Keyboard proximity on the Persian-ISIRI-9147 layout

Automatic detection is included — a document in this language is found before it is checked.

Set it up

gem install kotoshu
kotoshu setup fa

# optional, for semantic reranking
gem install onnxruntime
kotoshu setup fa --model                  # fluency, the default (~15 MB)
kotoshu setup fa --model --tier full      # maximum accuracy (~120 MB)

Notes

  1. 1.

    Keyboard-proximity suggestions use the Persian ISIRI 9147 layout.

  2. 2.

    The tokenizer includes ZWNJ so compounds like می‌روم stay whole — the staged dictionary carries tens of thousands of ZWNJ forms.

  3. 3.

    The fastText ONNX model is available for semantic reranking.