CLARIN.SI-embed.sl contains word embeddings induced from a large collection of Slovene texts composed of existing corpora of Slovene, e.g GigaFida, Janes, KAS, slWaC etc. The embeddings are based on the skip-gram model of fastText trained on 3,557,125,771 tokens of running text for (1) 2,466,596 lowercased surface forms (e.g., "slovenije") and (2) 2,093,848 lowercased lemmas with added part-of-speech information (e.g., "slovenija#Np").