veldhub / veld_data__fasttext_models

Data velds encapsulating fasttext wordembeddings models trained on the Austria Media Corpus.

Repository from Github https://github.comveldhub/veld_data__fasttext_modelsRepository from Github https://github.comveldhub/veld_data__fasttext_models

veld chain veld_data__fasttext_models

This repo contains data velds encapsulating static wordembeddings models trained on AMC at https://github.com/veldhub/veld_chain__train_infer_wordembeddings_multiple_architectures__amc/

This public repo does not contain the models themselves but only the metadata, due to licensing and storage issues. Best performing models will be published on other platforms once acceptable performance is achieved.

See inside the various data veld yaml files for information on each model.

About

Data velds encapsulating fasttext wordembeddings models trained on the Austria Media Corpus.

License:MIT License