A Python implementation of Farasa toolkit

Neural Arabic text diacritization

Yorùbá language training text for NLP, ASR and TTS tasks

Benchmark Arabic text diacritization dataset

Hebrew Diacritizer

Extensible DL-based automatic Arabic diacritization tool allowing the restoration of different types of diacritics.

Set of tools for tokenization, transliteration and diacritic restoration of a text written in Serbian language.

Automatic Arabic diacritics restoration tool.

Arabic deep-learning based diacritization models (Shakkala, Shakkelha) ported to PyTorch

Arabic deep-learning based diacritization models (Shakkala, Shakkelha) in the ONNX format.

Course Project for Natural Language Processing

Remove diacritics (accents)

Translation-over-Diacritization technique implementation

Neural Arabic text diacritization website

Official code for "Fine-Tashkeel at KSAA-2026" — Systematic evaluation of 18 Seq2Seq, token classification, decoder LLM, and ASR models for automatic Arabic text diacritization. 5th place at KSAA-2026 Shared Task (OSACT7 @ LREC 2026).

✒ DúöScríbî allows you to convert letters with diacritics to regular, ASCII letters. 🤓

Arabic diacritization with Transformers

A personal project on diacritizing Arabic text.

Guidelines and linguistic rules for improving Arabic pronunciation in AI speech systems through preprocessing and diacritization.

This repository implements a complete solution for processing Arabic text within PDF documents. Key features include: OCR using Google Cloud Document AI. Arabic text cleaning and formatting. Optional diacritization using Farasa. Asynchronous processing for faster performance.