Transformer models show improved accuracy for Quranic ASR

Researchers have conducted a comparative study on pretrained Transformer models for Quranic Automatic Speech Recognition (ASR), aiming to reduce high Word Error Rates (WER) on user-recited verses. The study fine-tuned models like Wav2Vec2.0, HuBERT, and XLS-R on an 870-hour Quranic dataset, identifying key factors for transcription accuracy. The best configuration achieved a WER of 0.08 on the EveryAyah subset, a significant improvement over the Citrinet baseline, while also reducing training time. AI

IMPACT Improves accuracy and efficiency for specialized ASR tasks, potentially aiding Quranic study and accessibility.

RANK_REASON Academic paper detailing a comparative study of AI models for a specific task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Citrinet
• EveryAyah
• Hubert
• Hugging Face
• Tartil
• transformer
• wav2vec2.0
• Wav2Vec2-XLSR-53
• XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →