Bakken & Baeck

Training a language model in spaCy v3

Words Nico Lutz

Intro

On Feb 1 2020, explosion.ai introduced spaCy v3, a huge upgrade to the previous version, featuring new transformer-based pipelines and workflows. Naturally some projects needed to be migrated to spaCy v3. This article shows in tutorial like steps what needs to be done to create a new language model from scratch.

This article assumes basic knowledge of python, spaCy and standard nlp techniques.

Test!

1 2 python -m venv .venv source .venv/bin/activate

Want to work with us? We'd love to hear from you.

Get in touch

(OSLO)

Bakken & Bæck AS
Trondheimsveien 135
0570 Oslo
Norway

(AMSTERDAM)

Bakken & Bæck B.V.
Van Diemenstraat 38
1013NH Amsterdam
The Netherlands

(BONN)

Bakken & Baeck GmBH
Fürstenstraße 2-4
53111 Bonn
Germany

(LONDON)

Bakken & Baeck LTD
23 Englefield Rd
London N1 4JX
United Kingdom