Cover Image

More Data, Fewer Diacritics: Scaling Arabic TTS

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Musleh, Ahmed, Zhang, Yifan, Darwish, Kareem
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Arabic Diacritics in the Wild: Exploiting Opportunities for Improved Diacritization
by: Elgamal, Salman, et al.
Published: (2024)

Creating Arabic LLM Prompts at Scale
by: El-Sheikh, Abdelrahman, et al.
Published: (2024)

Tool Calling for Arabic LLMs: Data Strategies and Instruction Tuning
by: Ersoy, Asim, et al.
Published: (2025)

Proper Noun Diacritization for Arabic Wikipedia: A Benchmark Dataset
by: Bondok, Rawan, et al.
Published: (2025)

A Language Modeling Approach to Diacritic-Free Hebrew TTS
by: Roth, Amit, et al.
Published: (2024)

Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study
by: Toyin, Hawau Olamide, et al.
Published: (2025)

Sadeed: Advancing Arabic Diacritization Through Small Language Model
by: Aldallal, Zeina, et al.
Published: (2025)

Arabic Text Diacritization In The Age Of Transfer Learning: Token Classification Is All You Need
by: Skiredj, Abderrahman, et al.
Published: (2024)

Interplay of Machine Translation, Diacritics, and Diacritization
by: Chen, Wei-Rui, et al.
Published: (2024)

Automatic Restoration of Diacritics for Speech Data Sets
by: Shatnawi, Sara, et al.
Published: (2023)

Don't Touch My Diacritics
by: Gorman, Kyle, et al.
Published: (2024)

Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning
by: Huang, Xijie, et al.
Published: (2023)

The Degree of Language Diacriticity and Its Effect on Tasks
by: Cohen, Adi, et al.
Published: (2026)

Hebrew Diacritics Restoration using Visual Representation
by: Elboher, Yair, et al.
Published: (2025)

Thaka at KSAA-2026 Task 2: Regularized Fine-Tuning for Arabic Speech Diacritization
by: Alamr, Meshal, et al.
Published: (2026)

Ramsa: A Large Sociolinguistically Rich Emirati Arabic Speech Corpus for ASR and TTS
by: Al-Sabbagh, Rania
Published: (2026)

Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions
by: Atif, Farah, et al.
Published: (2025)

Corpus-Based Approaches to Igbo Diacritic Restoration
by: Ezeani, Ignatius
Published: (2026)

Fanar 2.0: Arabic Generative AI Stack
by: FANAR TEAM, et al.
Published: (2026)

MuDRiC: Multi-Dialect Reasoning for Arabic Commonsense Validation
by: Elozeiri, Kareem, et al.
Published: (2025)

YAD: Leveraging T5 for Improved Automatic Diacritization of Yorùbá Text
by: Olawole, Akindele Michael, et al.
Published: (2024)

D-Nikud: Enhancing Hebrew Diacritization with LSTM and Pretrained Models
by: Rosenthal, Adi, et al.
Published: (2024)

Scaling Arabic Medical Chatbots Using Synthetic Data: Enhancing Generative AI with Synthetic Patient Records
by: Allam, Abdulrahman, et al.
Published: (2025)

On the importance of Data Scale in Pretraining Arabic Language Models
by: Ghaddar, Abbas, et al.
Published: (2024)

A Context-Contrastive Inference Approach To Partial Diacritization
by: ElNokrashy, Muhammad, et al.
Published: (2024)

AlpaGasus: Training A Better Alpaca with Fewer Data
by: Chen, Lichang, et al.
Published: (2023)

Evaluating Large Language Models for Diacritic Restoration in Romanian Texts: A Comparative Study
by: Nadas, Mihai, et al.
Published: (2025)

Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction
by: Fang, Yangui, et al.
Published: (2025)

ArEEG_Chars: Dataset for Envisioned Speech Recognition using EEG for Arabic Characters
by: Darwish, Hazem, et al.
Published: (2024)

ArEEG_Words: Dataset for Envisioned Speech Recognition using EEG for Arabic Words
by: Darwish, Hazem, et al.
Published: (2024)

Diacritic Restoration for Low-Resource Indigenous Languages: Case Study with Bribri and Cook Islands Māori
by: Coto-Solano, Rolando, et al.
Published: (2025)

F5-TTS-RO: Extending F5-TTS to Romanian TTS via Lightweight Input Adaptation
by: Chivereanu, Radu-Gabriel, et al.
Published: (2025)

Scaling Laws for Code: A More Data-Hungry Regime
by: Luo, Xianzhen, et al.
Published: (2025)

Abjad AI at NADI 2025: CATT-Whisper: Multimodal Diacritic Restoration Using Text and Speech Representations
by: Ghannam, Ahmad, et al.
Published: (2025)

Fanar: An Arabic-Centric Multimodal Generative AI Platform
by: Fanar Team, et al.
Published: (2025)

Entropy-Aligned Decoding of LMs for Better Writing and Reasoning
by: Ahmed, Kareem, et al.
Published: (2026)

AlcLaM: Arabic Dialectal Language Model
by: Ahmed, Murtadha, et al.
Published: (2024)

Instruction-Guided Poetry Generation in Arabic and Its Dialects
by: Sadallah, Abdelrahman, et al.
Published: (2026)

ARCADE: A City-Scale Corpus for Fine-Grained Arabic Dialect Tagging
by: Nacar, Omer, et al.
Published: (2026)

EMTSF:Extraordinary Mixture of SOTA Models for Time Series Forecasting
by: Alharthi, Musleh, et al.
Published: (2025)