israel's picture
Update README.md
b3af060
|
raw
history blame
No virus
363 Bytes
metadata
language:
  - amh
tags:
  - Amharic
  - Word Piece Tokenizer
  - Tokenizer
license: cc-by-4.0
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("israel/AmhWordPieceTokenizer")

encoding = tokenizer.encode("ኮሌጁ ቢያስተምርም ወደስራ የሚመድባቸው መንግስት ነው abcs")

encoding.tokens