Shakkelha

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Speech2 results

Arabic Text DiacritizationonTashkeela
Diacritic Error Rate· uses extra data· 2019-11-08
0.0169
best: 0.0113 (CBHG model)
SOTA
Neural Arabic Text Diacritization: State of the Art Results and a Novel Approach for Machine Translation arXiv:1911.03531
Arabic Text DiacritizationonTashkeela
Word Error Rate (WER)· uses extra data· 2019-11-08
0.0509
best: 0.0443 (CBHG model)
SOTA
Neural Arabic Text Diacritization: State of the Art Results and a Novel Approach for Machine Translation arXiv:1911.03531