Other
Evaluating End-to-End ASR for Qur'an recitation using whispers in low resource settings
Azzam Abdullah et al., Bulletin of Computer Science Research, 2025
Read the originalRead on October 17, 2026
- What it is
- A 2025 journal article that applies Whisper to recitations of 200 verses from Juz 30 of the Quran under low-resource conditions. It reports character error rate and processing time.
- How much weight it carries
- A single small study on one part of the Quran, using a curated dataset of short verses. The abstract reports only character error rate, so it says nothing about word error rate or tajweed.
Facts taken from this source
- In a 2025 study of 200 verses from Juz 30 of the Quran, Whisper reached an average character error rate of 0.142, which the authors describe as about 85 percent transcription accuracy.
“Whisper achieved an average CER of 0.142, corresponding to a transcription accuracy of about 85%” (Abstract)