phonsobon/khmer-G2P
Viewer β’ Updated β’ 38.6k β’ 51
A small character-level Transformer (7.5M parameters) that converts Khmer words to their
NCKL Khmer-script respelling, with - between syllables:
αααααΈ β ααα-ααΈ
Trained on phonsobon/khmer-G2P. Best validation word accuracy: 83.37% (epoch 150).
pip install khmer-g2p
khmer-g2p αααααΈ ααααα»ααΆ
from khmer_g2p import KhmerG2P
g2p = KhmerG2P() # downloads this repo
g2p("αααααΈ") # 'ααα-ααΈ'
g2p(["αααααα
", "ααααα»ααΆ"]) # list in, list out
model.safetensors β weightsconfig.json β model hyper-parameters and source/target vocabularieshistory.json, training_curves.png β training metrics