--- title: tigmorph · Tigre morphological analyzer emoji: 🔤 colorFrom: green colorTo: indigo sdk: static app_file: index.html pinned: true license: mit short_description: Morphological analyzer and generator for Tigre (ትግሬ) tags: - tigre - tig - morphology - morphological-analysis - finite-state - ethiopic - geez - low-resource datasets: - BeitTigreAI/tigre-data-monolingual-text --- # tigmorph · Tigre morphological analyzer Interactive demo of [tigmorph](https://github.com/beshir-a-Ibrahim/tigmorph), a morphological analyzer and generator for **Tigre** (ትግሬ, Ge'ez script) built from Shlomo Raz, *A Descriptive Study of Tigre Grammar* (1973). The analyzer runs entirely in the visitor's browser with [Pyodide](https://pyodide.org): tigmorph is pure Python with no dependencies, so this is a static Space with no server. - **Analyze**: words or whole sentences, giving root or lemma, word class, features, pronunciation in Raz's transcription and an English gloss, ranked by a model learned from an 11-million-word Tigre corpus. - **Generate**: any form from a root and features, or a full paradigm. - **Normalize**: rewrite text in one standard spelling. ## Files | File | What it is | |---|---| | `index.html` | the page | | `web.py` | small glue layer between the page and tigmorph | | `tigmorph.zip` | the `tigmorph/` package folder from GitHub, zipped (code and compiled transducers) | To update after changing tigmorph, rebuild the zip from the repository root and upload it: ```bash zip -r tigmorph.zip tigmorph -x '*/__pycache__/*' ``` Code MIT; data CC0 / CC BY 4.0 / CC BY-SA 4.0 by source (see the repository's LICENSE-DATA.md). If you use tigmorph, please cite it and Raz (1973).