Bakken & Baeck

Training a language model in spaCy v3

Words Nico Lutz


On Feb 1 2020, 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.


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


Bakken & Bæck AS
Trondheimsveien 135
0570 Oslo


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


Bakken & Baeck GmBH
Fürstenstraße 2-4
53111 Bonn


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