py-bpemb

v 0.3.5 Updated: 4 weeks ago

Byte pair embeddings in 275 languages

BPEmb is a collection of pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) and trained on Wikipedia. Its intended use is as input for neural models in natural language processing.

BPEmb is a collection of pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) and trained on Wikipedia. Its intended use is as input for neural models in natural language processing.

+ Show more

https://nlp.h-its.org/bpemb

Installable ports: