
bpemb
by bheinzerling (personal account)
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) (description from the project’s GitHub page)
Repository facts
- Stars
- 1,227
- Forks
- 100
- Open issues and pull requests
- 6
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- bheinzerling · Personal account
- Created
- Oct 4, 2017
- Last push
- Oct 1, 2024
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 7,103: nlp-uoregon/trankit
Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing
798 starsPythonApache-2.0Last push Jul 22, 2025
Rank 2,309: superlinked/sie
Open-source inference server and production cluster for all the models your agent needs.
3,410 starsPythonApache-2.0Last push Oct 18, 2026
Rank 4,226: plasticityai/magnitude
A fast, efficient universal vector embedding utility package.
1,674 starsPythonMITLast push Aug 3, 2023
Rank 6,215: wikipedia2vec/wikipedia2vec
A tool for learning vector representations of words and entities from Wikipedia
973 starsPythonOther licenseLast push May 3, 2024
Rank 7,871: Santosh-Gupta/SpeedTorch
Library for faster pinned CPU <-> GPU transfer in Pytorch
682 starsPythonMITLast push Feb 21, 2020