GitHub · #665

google/sentencepiece

google/sentencepiece is #665 in this GitHub directory, with 12,138 stars. Unsupervised text tokenizer for Neural Network-based text generation.

Repository: https://github.com/google/sentencepiece
Homepage: https://google.github.io/sentencepiece/
Owner: google (Organization)
Stars: 12,138
Forks: 1,387
Open issues: 6
Language: C++
License: Apache-2.0
Created: 2017-03-07
Last push: 2026-10-17
Topics: natural-language-processing, neural-machine-translation, word-segmentation
Snapshot: 2026-10-18