khmerns 0.0.3

Khmer Neural Segmenter

Khmer Neural Segmenter

A fast Khmer word segmentation library.

Installation

pip install khmerns

Usage

from khmerns import tokenize

# Returns a list of words
words = tokenize("សួស្តីបងប្អូន")
# ['សួស្តី', 'បង', 'ប្អូន']

You can also use the class-based API if you prefer:

from khmerns import KhmerSegmenter

segmenter = KhmerSegmenter()
words = segmenter.tokenize("សួស្តីបងប្អូន")
# or
words = segmenter("សួស្តីបងប្អូន")

Training

The training pipeline lives in the training/ directory. It trains a BiGRU + CRF model on character-level BIO tags, then converts the result to GGUF for the C++ inference backend.

Data format

Training data is a plain text file at training/data/train.txt. One word per line. Words that appear on consecutive lines are treated as part of the same sentence. The model learns word boundaries from this.

Example training/data/train.txt:

សួស្តី
បង
ប្អូន
ខ្ញុំ
ទៅ
ផ្សារ

Non-Khmer tokens (spaces, punctuation, numbers, Latin text) are tagged as NON-KHMER. Khmer tokens get B-WORD on the first character and I-WORD on the rest.

Steps

cd training
pip install -r requirements.txt

1. Prepare training data

Place your segmented text in data/train.txt (one word per line). If you have raw unsegmented Khmer text, you can use the generation script to pre-segment it:

python generate.py

This requires khmersegment and a source text file. Edit the path in generate.py to point to your raw text.

2. Train

python train.py

Trains for 20 epochs with AdamW (lr=1e-5) and ReduceLROnPlateau. Saves best_model.pt (best eval loss) and model.pt (final). Uses CUDA if available.

3. Convert to GGUF

python convert_to_gguf.py best_model.pt model.gguf

This produces a GGUF file (~3.3MB) containing all model weights.

4. Embed in the C++ binary

To use the new model in the library, convert the GGUF file to a C header and replace src/model_data.h, then rebuild:

xxd -i model.gguf > ../src/model_data.h
pip install -e ..

License

MIT