Shakkala

Reported on 4 benchmarks across 1 task · 2 papers · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech4 results

Arabic Text DiacritizationonTashkeela
Diacritic Error Rate· 2019-04-25
0.0373
best: 0.0113 (CBHG model)
SOTA
Arabic Text Diacritization Using Deep Neural Networks arXiv:1905.01965
Arabic Text DiacritizationonTashkeela
Word Error Rate (WER)· 2019-04-25
0.1119
best: 0.0443 (CBHG model)
SOTA
Arabic Text Diacritization Using Deep Neural Networks arXiv:1905.01965
Arabic Text DiacritizationonCATT
DER(%)· 2024-07-03
13.494
best: 58.313 (Deep Diacritization (D3))
CATT: Character-based Arabic Tashkeel Transformer arXiv:2407.03236
Arabic Text DiacritizationonCATT
WER (%)· 2024-07-03
50.387
best: 34.191 (CATT ED)
CATT: Character-based Arabic Tashkeel Transformer arXiv:2407.03236