tokenizers.bpe: Byte Pair Encoding Text Tokenization

Unsupervised text tokenizer focused on computational efficiency. Wraps the 'YouTokenToMe' library <> which is an implementation of fast Byte Pair Encoding (BPE) <>.

Version: 0.1.3
Depends: R (≥ 2.10)
Imports: Rcpp (≥ 0.11.5)
LinkingTo: Rcpp
Published: 2023-09-15
DOI: 10.32614/CRAN.package.tokenizers.bpe
Author: Jan Wijffels [aut, cre, cph] (R wrapper), BNOSAC [cph] (R wrapper), [cph], Gregory Popovitch [ctb, cph] (Files at src/parallel_hashmap (Apache License, Version 2.0), The Abseil Authors [ctb, cph] (Files at src/parallel_hashmap (Apache License, Version 2.0), Ivan Belonogov [ctb, cph] (Files at src/youtokentome (MIT License))
Maintainer: Jan Wijffels <jwijffels at>
License: MPL-2.0
NeedsCompilation: yes
Materials: README NEWS
In views: NaturalLanguageProcessing
CRAN checks: tokenizers.bpe results


Reference manual: tokenizers.bpe.pdf


Package source: tokenizers.bpe_0.1.3.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): tokenizers.bpe_0.1.3.tgz, r-oldrel (arm64): tokenizers.bpe_0.1.3.tgz, r-release (x86_64): tokenizers.bpe_0.1.3.tgz, r-oldrel (x86_64): tokenizers.bpe_0.1.3.tgz
Old sources: tokenizers.bpe archive

Reverse dependencies:

Reverse suggests: doc2vec, sentencepiece, textrecipes


Please use the canonical form to link to this page.