---
license: bsd-3-clause
language: ar
inference: false
tags:
  - secryst
  - transliteration
  - diacritization
  - onnx
  - byt5
---

# ara-diac-2.0-int8

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-int8")
```

- Artifact: `ara-diac-2.0-int8.zip` (0.48 GiB)

## 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 |

## 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.