yannvgn/laserembeddings

LASER multilingual sentence embeddings as a pip package

60
/ 100
Established

Replaces heavy C++ dependencies (Moses, fastBPE) with pure-Python alternatives (Sacremoses, subword-nmt) for zero-config installation. Produces language-agnostic 1024-dimensional vectors using Facebook Research's pre-trained encoder, enabling zero-shot cross-lingual transfer and multilingual semantic similarity tasks. Supports 93+ languages with optional tokenization extras for Chinese (jieba) and Japanese (MeCab).

224 stars and 2,671 monthly downloads. Used by 1 other package. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 19 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

224

Forks

29

Language

Python

License

BSD-3-Clause

Last pushed

Aug 11, 2023

Monthly downloads

2,671

Commits (30d)

0

Dependencies

5

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/yannvgn/laserembeddings"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.