Acknowledgements
This project is built on the shoulders of many incredible open-source libraries, tools, and fonts. We are deeply grateful to every maintainer and contributor who makes this possible.
Libraries & Frameworks
Khmer Coeng Ta/Da Corrector
Special thanks to Mr. Seanghay Yath for the originalKhmer Coeng Ta/Da Correctorproject, including its trained model, C++ engine, and browser WASM implementation.
123 Toolbox uses the original browser WASM artifacts with attribution under the MIT License. Theoriginal deployed demoremains available from the author.
Copyright © 2026 Seanghay Yath · MIT License
Khmer Word Segmentation
Special thanks to Mr. Seanghay Yath for the originalsplit-khmerpackage, which powers the Khmer sentence-to-word-array segmentation in the Word Segmentation Tester.
The package is used under the MIT License and remains credited to its original author.
Copyright © Seanghay Yath · MIT License
The comparison references the vengmony/khmer-nlp-toolkit JavaScript toolkit under the MIT License and the vvearr/khmer-word-segmentation KCC and annotation project under Apache-2.0.
Sovichea’s Khmer Viterbi Segmenter is provided as an external reference. Its project code is MIT licensed, while bundled linguistic data has separate noncommercial terms. We link to its live demo and do not redistribute its restricted data.
Khmer Punctuation Restoration
The punctuation-restoration tool references khmerpunctuate by Seanghay Yath and its Khmer punctuation model on Hugging Face.
The current browser fallback is independently implemented and does not bundle the original ONNX model. The original project is credited for the reference workflow and model approach under the MIT License.
Fonts
Infrastructure
Built with care by im4tta and contributors.