File size: 744 Bytes
bf4dfc2 e5bd3ab 4d48c1f bf4dfc2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 |
from datasets import load_dataset
from tokenizers import trainers, Tokenizer, normalizers, ByteLevelBPETokenizer
# load dataset
# dataset = load_dataset("mc4", "sw", split="train")
dataset = load_dataset("text", "sw", split="train", data_files={"train": ["/home/shared/clean_swahili/train_v1.4.txt"]})
# Instantiate tokenizer
tokenizer = ByteLevelBPETokenizer()
def batch_iterator(batch_size=1000):
for i in range(0, len(dataset), batch_size):
yield dataset[i: i + batch_size]["text"]
# Customized training
tokenizer.train_from_iterator(batch_iterator(), vocab_size=25165, min_frequency=2, special_tokens=[
"<s>",
"<pad>",
"</s>",
"<unk>",
"<mask>",
])
# Save files to disk
tokenizer.save("tokenizer.json")
|