File size: 626 Bytes
2835721
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
#!/usr/bin/env python3
from datasets import load_dataset
from tokenizers import ByteLevelBPETokenizer

# Load dataset
dataset = load_dataset("large_spanish_corpus", split="train")
# Instantiate tokenizer
tokenizer = ByteLevelBPETokenizer()
def batch_iterator(batch_size=100_000_000):
    for i in range(0, len(dataset), batch_size):
        yield dataset["text"][i: i + batch_size]
# Customized training
tokenizer.train_from_iterator(batch_iterator(), vocab_size=50265, min_frequency=2, special_tokens=[
    "<s>",
    "<pad>",
    "</s>",
    "<unk>",
    "<mask>",
])
# Save files to disk
tokenizer.save("./tokenizer.json")