A test of Hidden Markov Model converter from lomaji to hanji of Taiwanese (Hokkien). still in alpha version.
- Python3
- Pandas
usage: pakkau.py [-h] [--genmod] [--form FORM] [SENTENCE]
positional arguments:
SENTENCE the sentence to be converted
options:
-h, --help show this help message and exit
--genmod generate the model
--form FORM the orthography to be used (poj or tl). Default is poj. (not opened)
python3 ./pakkau.py --form tl "Lāu-su kóng: \"ta̍k-ke tsò-hué lâi\""
output:
老師講:"逐家做伙來"
python3 ./pakkau.py --genmod
generate models from the .csv parallel transliteration file in ./corpus files
- poj conversion
- the preciseness of the conversion