πŸ† #133 overall#56 of 1,075 in Natural Language ProcessingπŸ”₯ active this week

google /sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

$ git clone https://github.com/google/sentencepiece.git
GitHub social preview for google/sentencepiece
Stars
12.1K
12,096
Forks
1.4K
1,381
Language
C++
License
Apache-2.0
Created
Mar 7, 2017
9.5 years old
Last push
Sep 22, 2026
πŸ”₯ this week

Categories

GitHub topics

More in Natural Language Processing

Natural Language Processing

NiuTrans/MTBook

γ€ŠζœΊε™¨ηΏ»θ―‘οΌšεŸΊη‘€δΈŽζ¨‘εž‹γ€‹θ‚–ζ‘ ζœ±ι–ζ³’ θ‘— - Machine Translation: Foundations and Models

🌍 Machine Translation
TeXno licenseupdated Sep 14, 2024
GitHub β†—β˜… 2.8Kβ‘‚ 747
Natural Language Processing

delip/PyTorchNLPBook

Code and data accompanying Natural Language Processing with PyTorch published by O'Reilly Media https://amzn.to/3JUgR2L

Jupyter NotebookApache-2.0updated Mar 12, 2023
GitHub β†—β˜… 2.1Kβ‘‚ 806
Natural Language Processing

OpenNMT/OpenNMT-tf

Neural machine translation and sequence learning using TensorFlow

🌍 Machine Translation
PythonMITupdated Oct 14, 2023
GitHub β†—β˜… 1.5Kβ‘‚ 378
Natural Language Processing

lyeoni/nlp-tutorial

A list of NLP(Natural Language Processing) tutorials

πŸ—‚οΈ Text Classification
Jupyter NotebookMITupdated Apr 1, 2020
GitHub β†—β˜… 1.4Kβ‘‚ 261
Natural Language Processing

Helsinki-NLP/Opus-MT

Open neural machine translation models and web services

🌍 Machine Translation
PythonMITupdated Feb 23, 2026
GitHub β†—β˜… 864β‘‚ 91
Natural Language Processing

taishi-i/nagisaπŸ”₯ active

A Japanese tokenizer based on recurrent neural networks

βœ‚οΈ Tokenization & Preprocessing
PythonMITupdated Sep 22, 2026
GitHub β†—β˜… 420β‘‚ 23

Data from GitHub Β· snapshot Sep 24, 2026