Challenges / mcit

Khaliji Speech Recognition Challenge 2025

CompletedStatisticsMetric: WERmcMCIT
QAR 250,000 + fast-track to marketplace
Deadline 2025-06-30 29 participants

Transcribe conversational Gulf Arabic from government contact-centre calls, spanning Qatari, Bahraini, and Emirati accents with heavy English code-switching. Sadeem AI's winning system achieved 11.4 WER and was published to the marketplace as khaliji-asr, now powering voice services across three ministries.

Winning model published to the marketplace

Sadeem AI's Khaliji ASR passed the RAI pipeline and is live in the catalog.

View model card

Leaderboard

Scored on WER: lower is better
RankTeamOrganisationWERSubmissions
1Sadeem AISadeem AI11.438
2QCRI SpeechLabHBKU12.145
3HBKU VoiceTechHBKU13.831
4Wahaj LabsWahaj Labs15.219
5@abdulrahman_asrindependent16.723
6Falak AnalyticsFalak Analytics17.912
7@leila_speechindependent19.315
8@vikram_audioindependent21.69
9HBKU MSc Cohort AHBKU24.18
10@khalifa_devindependent27.54

Note: this challenge is scored on WER (word error rate), so lower scores are better, Sadeem AI's winning 11.4 WER leads the board.

Submit an entry

Submission upload disabled

This challenge has concluded

Challenge closed

Teams must be registered on the platform. Submissions are evaluated on a held-out national test set and logged to the audit trail.