🏆 #1,262 overall#426 of 2,559 in Natural Language Processing

bheinzerling /bpemb

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

$ git clone https://github.com/bheinzerling/bpemb.git
GitHub social preview for bheinzerling/bpemb
Stars
1.2K
1,229
This week
+1 ★
Forks
100
100
Language
Python
License
MIT
Created
Oct 4, 2017
9.1 years old
Last push
Oct 1, 2024

Stars, last 17 days

Oct 28, 2026 → Nov 16, 2026
★ 1.2K▲ +2★ 1.2K

Categories

GitHub topics

More in Natural Language Processing

Natural Language Processing

plasticityai/magnitude

A fast, efficient universal vector embedding utility package.

🧬 Embeddings
PythonMITupdated Aug 3, 2023
GitHub ↗★ 1.7K⑂ 125
Natural Language Processing

roshan-research/hazm

▲ +1 ★ this week

Persian NLP Toolkit

✂️ Tokenization & Preprocessing💎 Text Mining
PythonMITupdated Apr 1, 2026
GitHub ↗★ 1.4K⑂ 208
Natural Language Processing

wikipedia2vec/wikipedia2vec

▲ +1 ★ this week

A tool for learning vector representations of words and entities from Wikipedia

🗂️ Text Classification
PythonOtherupdated May 3, 2024
GitHub ↗★ 976⑂ 101
Natural Language Processing

curiosity-ai/catalyst

▲ +3 ★ this week

🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.

C#MITupdated Oct 8, 2026
GitHub ↗★ 864⑂ 86
Natural Language Processing

RelevanceAI/relevanceai

Home of the AI workforce - Multi-agent system, AI agents & tools

PythonApache-2.0updated Jan 15, 2026
GitHub ↗★ 286⑂ 50
Natural Language Processing

lgalke/vec4ir

Word Embeddings for Information Retrieval

🧬 Embeddings🔍 Search & Retrieval
PythonMITupdated Oct 4, 2023
GitHub ↗★ 227⑂ 39

Data from GitHub · snapshot Nov 16, 2026