| --- |
| license: bsd-3-clause |
| language: ar |
| inference: false |
| tags: |
| - secryst |
| - transliteration |
| - diacritization |
| - onnx |
| - byt5 |
| --- |
| |
| # ara-diac-2.0 |
|
|
| Part of the [Secryst](https://secryst.github.io) phonological-layer family — a dedicated model for **diacritization** (AR), distributed as a Secryst IMF artifact and loadable through any Secryst crystal: |
|
|
| ```python |
| from secryst import Model |
| Model.load("ara-diac-2.0") |
| ``` |
|
|
| - Artifact: `ara-diac-2.0-fp32.zip` (2.59 GiB) |
| - Precision variants: `ara-diac-2.0-int8` |
|
|
| ## Measured quality |
|
|
| Full evaluation sets, zero skipped examples, the benchmark's own evaluator. Provenance for every number is the results record of the training project. |
|
|
| | metric | value | provenance | |
| |---|---|---| |
| | der_total_greedy | 2.2864 | rababa/docs/RESULTS.md#r7-verdict-table-sadeeddiac-25-2026-08-28 | |
| | der_morph_greedy | 1.3343 | rababa/docs/RESULTS.md#r7-verdict-table-sadeeddiac-25-2026-08-28 | |
| | wer_wikinews_multiref | 17.3794 | rababa/docs/RESULTS.md#r7-ood-verdict-table-wikinews-2024-multiref-2026-08-28 | |
| | der_wikinews_multiref | 11.8273 | rababa/docs/RESULTS.md#r7-ood-verdict-table-wikinews-2024-multiref-2026-08-28 | |
|
|
| ## Benchmark |
|
|
| SadeedDiac-25 — full 1,200-paragraph set, Misraj's evaluator, zero |
| skipped examples, greedy decode (protocol-matched published numbers |
| only): |
|
|
| | system | Total DER | kind | |
| |---|---|---| |
| | Claude-3.7-Sonnet | 1.39% | frontier LLM | |
| | **ara-diac-2.0 (this model)** | **2.29%** | dedicated, 580M | |
| | GLM-5.2 | 2.69% | frontier LLM | |
| | Gemini-Flash-2.0 | 3.19% | frontier LLM | |
| | GPT-4 | 3.86% | frontier LLM | |
| | Sadeed-1.5B | 7.29% | leaderboard baseline | |
|
|
| Word-final iʿrāb endings (the hardest component): 1.33% DER. |
| Out-of-domain generalization (WikiNews-2024 multi-reference): |
| 17.38 WER / 11.83 DER. |
|
|
| ## Architecture |
|
|
| ByT5-large-class seq2seq transformer (580M parameters), byte-level |
| input/output (no tokenizer — id = byte + 3). Trained on classical and |
| modern Arabic running text with a news-domain adaptation stage over a |
| morphology-auxiliary curriculum. The canonical distribution is the |
| Secryst IMF artifact (sha256-verified, parity-gated against the |
| PyTorch reference); this repository mirrors those exact bytes. |
|
|
|
|
| ## License |
|
|
| BSD-3-CLAUSE |
|
|
| ## Provenance |
|
|
| Trained in the [Secryst training monorepo](https://github.com/secryst/secryst-train) and published through the [interscript-ml](https://github.com/interscript/interscript-ml) distribution contract (models.yaml index, sha256-verified release assets, parity-gated artifacts). The canonical download channel is GitHub Releases; this repository is the Hugging Face mirror of the same bytes, pinned to the index revision. |
|
|
