# grapheme-kit: Grapheme-Level Metrics and Text Processing for Multilingual NLP

arXiv: https://arxiv.org/abs/2607.22456 · HTML: https://mlsanity.com/paper/2607.22456/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [Language Model Tokenizers Introduce Unfairness Between Languages](https://mlsanity.com/paper/2305.15425/) (2023)
- [Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP World](https://mlsanity.com/paper/2210.08523/) (2022)
- [Survey on Publicly Available Sinhala Natural Language Processing Tools and Research](https://mlsanity.com/paper/1906.02358/) (2019)
- [DEMETR: Diagnosing Evaluation Metrics for Translation](https://mlsanity.com/paper/2210.13746/) (2022)
- [Advocating Character Error Rate for Multilingual ASR Evaluation](https://mlsanity.com/paper/2410.07400/) (2024)
- [Egalitarian Language Representation in Language Models: It All Begins with Tokenizers](https://mlsanity.com/paper/2409.11501/) (2024)
- [string2string: A Modern Python Library for String-to-String Algorithms](https://mlsanity.com/paper/2304.14395/) (2023)
- [Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla](https://mlsanity.com/paper/2507.01931/) (2025)
- [Neural Grapheme-to-Phoneme Conversion with Pre-trained Grapheme Models](https://mlsanity.com/paper/2201.10716/) (2022)
- [GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer](https://mlsanity.com/paper/2509.18081/) (2025)

## Built on by (most cited first, 1 of 1)

- [Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR](https://mlsanity.com/paper/2610.20461/) (2026)

## Abstract (arXiv)

Existing lexical distance, similarity, and evaluation metrics operate on Unicode code points, which can misrepresent errors in writing systems where a single grapheme is represented by multiple Unicode code points. We introduce grapheme-kit, an open-source Python library that extends these metrics to operate on grapheme clusters instead. The library also provides improved grapheme processing for Tamil and Sinhala, including accurate grapheme cluster identification and grapheme composition/decomposition utilities. Through an OCR case study, we demonstrate that grapheme-level metrics provide a more faithful evaluation of complex scripts.