Croatian Text Diacritization

"Croatian Text Diacritization" is a subtask in the field of natural language processing, aiming to add the correct diacritical marks to letters in Croatian text. The goal of this task is to automatically identify and label the appropriate diacritical marks for each letter in a Croatian text that lacks these marks, restoring its standard written form. This not only helps improve the readability and accuracy of the text but also holds significant value for applications such as machine translation and speech synthesis.