issues
search
ybracke
/
transnormer
A lexical normalizer for historical spelling variants using a transformer architecture.
GNU General Public License v3.0
6
stars
1
forks
source link
Custom tokenizer as a separate module
#31
Closed
ybracke
closed
1 year ago
ybracke
commented
1 year ago
[x] Move customized normalizer for huggingface tokenizers ("transliterator") from
train_model.py
into its own module (-->
transnormer.preprocess.translit
)
[x] Create tests
[x] Use new functionality in
train_model.py
train_model.py
into its own module (-->transnormer.preprocess.translit
)train_model.py