bpemb
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)
bheinzerling/bpemb
View on GitHub ↗Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)
bpemb grew +0.2% in the last 30 days, ranks 7th of 14 in Embedding & Reranker Models, last commit 754 days ago.
Star trajectory
115 days tracked2026-07-021.2k stars today2026-10-25
Momentum
+0.2% in 30d, above the Embedding & Reranker Models median of +0.1%.
Maintenance
Last commit 754 days ago, staler than the median of 566.5d.
How it compares in Embedding & Reranker Models
bpemb
1.2k
stars
+0.2% 30d
commit 754 days ago
Embedding & Reranker Models median
1.1k
stars
+0.1% 30d
commit ~566.5d ago
Leader · ailia-models
2.4k
stars
+0.4% 30d
commit 2 days ago
Ranked 7th of 14 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 7
- Forks
- 100
- Watchers
- 23
- Open issues
- 4
- Releases
- 0
- Created
- 2017-10-04
- Stars this week
- +0
You've seen where bpemb stands today.
Get the moves before everyone else: the 5 Embedding & Reranker Models repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.