@inproceedings{esmaeil-etal-2026-tantaarabnlp,
title = "{T}anta{A}rab{NLP} at {KSAA}-2026 Task 2: Adapting {CATT}-Whisper for {A}rabic Speech Dictation with Automatic Diacritization",
author = "Esmaeil, Nada Adel and
Elbasiony, Reda M. and
Faheem, Mohamed T.",
editor = "Al-Khalifa, Hend and
El-Haj, Mo and
Ezzini, Saad",
booktitle = "The 7th Workshop on Open-Source {A}rabic Corpora and Processing Tools ({OSACT}7) with 5 Shared Tasks",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.osact-1.30/",
doi = "10.63317/46cm97fcekow",
pages = "229--233",
abstract = "We present our submission to the KSAA-2026 Shared Task (Subtask 2): Automatic Diacritization of Speech Dictation. Building upon the CATT-Whisper multimodal architecture, which fuses representations from a pre-trained CATT text encoder and the Whisper speech encoder, we fine-tune the model end-to-end on the official shared task training data. To further enhance performance on speech-dictated Arabic text, we apply careful post-processing to the model outputs. Our best submission achieves a Diacritic Error Rate (DER) of 7.04, a Word Error Rate (WER) of 24.39, and a Sentence Error Rate (SER) of 71.65 on the hidden test set, securing 2nd place in the competition. These results demonstrate the effectiveness of adapting a strong multimodal baseline to the speech-aware diacritization setting and highlight the value of task-specific fine-tuning and output refinement for bridging the gap between spoken transcripts and fully diacritized Arabic text."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="esmaeil-etal-2026-tantaarabnlp">
<titleInfo>
<title>TantaArabNLP at KSAA-2026 Task 2: Adapting CATT-Whisper for Arabic Speech Dictation with Automatic Diacritization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nada</namePart>
<namePart type="given">Adel</namePart>
<namePart type="family">Esmaeil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reda</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Elbasiony</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Faheem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saad</namePart>
<namePart type="family">Ezzini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present our submission to the KSAA-2026 Shared Task (Subtask 2): Automatic Diacritization of Speech Dictation. Building upon the CATT-Whisper multimodal architecture, which fuses representations from a pre-trained CATT text encoder and the Whisper speech encoder, we fine-tune the model end-to-end on the official shared task training data. To further enhance performance on speech-dictated Arabic text, we apply careful post-processing to the model outputs. Our best submission achieves a Diacritic Error Rate (DER) of 7.04, a Word Error Rate (WER) of 24.39, and a Sentence Error Rate (SER) of 71.65 on the hidden test set, securing 2nd place in the competition. These results demonstrate the effectiveness of adapting a strong multimodal baseline to the speech-aware diacritization setting and highlight the value of task-specific fine-tuning and output refinement for bridging the gap between spoken transcripts and fully diacritized Arabic text.</abstract>
<identifier type="citekey">esmaeil-etal-2026-tantaarabnlp</identifier>
<identifier type="doi">10.63317/46cm97fcekow</identifier>
<location>
<url>https://aclanthology.org/2026.osact-1.30/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>229</start>
<end>233</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TantaArabNLP at KSAA-2026 Task 2: Adapting CATT-Whisper for Arabic Speech Dictation with Automatic Diacritization
%A Esmaeil, Nada Adel
%A Elbasiony, Reda M.
%A Faheem, Mohamed T.
%Y Al-Khalifa, Hend
%Y El-Haj, Mo
%Y Ezzini, Saad
%S The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma, Mallorca (Spain)
%F esmaeil-etal-2026-tantaarabnlp
%X We present our submission to the KSAA-2026 Shared Task (Subtask 2): Automatic Diacritization of Speech Dictation. Building upon the CATT-Whisper multimodal architecture, which fuses representations from a pre-trained CATT text encoder and the Whisper speech encoder, we fine-tune the model end-to-end on the official shared task training data. To further enhance performance on speech-dictated Arabic text, we apply careful post-processing to the model outputs. Our best submission achieves a Diacritic Error Rate (DER) of 7.04, a Word Error Rate (WER) of 24.39, and a Sentence Error Rate (SER) of 71.65 on the hidden test set, securing 2nd place in the competition. These results demonstrate the effectiveness of adapting a strong multimodal baseline to the speech-aware diacritization setting and highlight the value of task-specific fine-tuning and output refinement for bridging the gap between spoken transcripts and fully diacritized Arabic text.
%R 10.63317/46cm97fcekow
%U https://aclanthology.org/2026.osact-1.30/
%U https://doi.org/10.63317/46cm97fcekow
%P 229-233
Markdown (Informal)
[TantaArabNLP at KSAA-2026 Task 2: Adapting CATT-Whisper for Arabic Speech Dictation with Automatic Diacritization](https://aclanthology.org/2026.osact-1.30/) (Esmaeil et al., OSACT 2026)
ACL