File size: 1,097 Bytes
e13e012
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
27
28
29
30
31
32
33
34
35
from datasets import load_dataset, concatenate_datasets
from tokenizers import trainers, Tokenizer, normalizers
from t5_tokenizer_model import SentencePieceUnigramTokenizer


vocab_size = 50_000
input_sentence_size = None
model_dir = "./"  # ${MODEL_DIR}

# Initialize a dataset
dataset = load_dataset("json", data_files=["/mnt/disks/flaxdisk/corpus/norwegian_colossal_corpus_validation.json","/mnt/disks/flaxdisk/corpus/special_chars.json"], split='train')

tokenizer = SentencePieceUnigramTokenizer(unk_token="<unk>", eos_token="</s>", pad_token="<pad>")


# Build an iterator over this dataset
def batch_iterator(input_sentence_size=None):
    if input_sentence_size is None:
        input_sentence_size = len(dataset)
    batch_length = 100
    for i in range(0, input_sentence_size, batch_length):
        yield dataset[i: i + batch_length]["text"]


# Train tokenizer
tokenizer.train_from_iterator(
    iterator=batch_iterator(input_sentence_size=input_sentence_size),
    vocab_size=vocab_size,
    show_progress=True,
)

# Save files to disk
tokenizer.save(f"{model_dir}/tokenizer.json")