Hello! First of all, thank you for such a great product!
Do you have a model for breaking text into sentences for English and Russian texts (pyTorch preferably)? I couldn’t find it in the documentation.
Hi, @vzhilov
The only model we have is deeppavlov/configs/sentence_dailydialog.json - restoration of punctuation in English and this model is TF-based.
Thank you very much for the answer. I have realized the final result I’m trying to achieve is to make search suggestions for our Solr search system. So maybe not the sentence breaker, but maybe some other model you have that can get trained on existing data to suggest search phrase completion or propose alternative search phrases?
Solr can do that if we feed it with text broken on sentences, but that doesn’t work good.