#Amhtokenizer

Showing 1 of 1 repositories tagged #amhtokenizer, ranked by stars

Amharic-Tokenizer

Syllable-aware BPE tokenizer for the Amharic language (አማርኛ) – fast, accurate, trainable.

★ 100 ⑂ 15 —

Related Topics

#african-languages #amharic #amharic-tokenizer #amharictokenizer #bpe #bpe-tokenizer #deep-learning #ethiopic #language-processing #llm #low-resource-languages #machine-learning