sentencepiece

# Command-line (BPE with 8000 vocab)
spm_train --input=data.txt --model_prefix=m --vocab_size=8000 --model_type=bpe
 
# Python API
import sentencepiece as spm
 
spm.SentencePieceTrainer.train(
    input='data.txt',
    model_prefix='m',
    vocab_size=8000,
    model_type='bpe'
)

import sentencepiece as spm
 
# Load model
sp = spm.SentencePieceProcessor(model_file='m.model')
 
# Encode to pieces
pieces = sp.encode('This is a test', out_type=str)
print(pieces)  # ['▁This', '▁is', '▁a', '▁test']
 
# Encode to IDs
ids = sp.encode('This is a test', out_type=int)
print(ids)  # [284, 47, 11, 1243]
 
# Decode
text = sp.decode(ids)
print(text)  # "This is a test"

text = "Hello world"
pieces = sp.encode(text, out_type=str)
print(pieces)  # ['▁Hello', '▁world']
 
# Decode preserves spaces
decoded = sp.decode_pieces(pieces)
print(decoded)  # "Hello world"

spm.SentencePieceTrainer.train(
    input='data.txt',
    model_prefix='bpe_model',
    vocab_size=16000,
    model_type='bpe'
)

spm.SentencePieceTrainer.train(
    input='data.txt',
    model_prefix='unigram_model',
    vocab_size=8000,
    model_type='unigram'
)

spm.SentencePieceTrainer.train(
    input='corpus.txt',
    model_prefix='m',
    vocab_size=32000,
    model_type='unigram',
    character_coverage=0.9995,  # 1.0 for CJK
    user_defined_symbols=['[SEP]', '[CLS]'],
    unk_piece='<unk>',
    num_threads=16
)

# Sample different tokenizations
for _ in range(3):
    pieces = sp.encode('tokenization', out_type=str, enable_sampling=True, alpha=0.1)
    print(pieces)
 
# Output (different each time):
# ['▁token', 'ization']
# ['▁tok', 'en', 'ization']

spm.SentencePieceTrainer.train(
    input='c4_corpus.txt',
    model_prefix='t5',
    vocab_size=32000,
    model_type='unigram',
    user_defined_symbols=[f'<extra_id_{i}>' for i in range(100)],
    unk_id=2,
    eos_id=1,
    pad_id=0
)

from transformers import T5Tokenizer
 
# T5 uses SentencePiece internally
tokenizer = T5Tokenizer.from_pretrained('t5-base')
inputs = tokenizer('translate English to French: Hello', return_tensors='pt')