kiri-ai/distiluse-base-multilingual-cased-et

The model is based off Sentence-Transformer's distiluse-base-multilingual-cased multilingual model that has been extended to understand sentence embeddings in Estonian . The model was fine-tuned on English-Estonian parallel sentences taken from OPUS and ParaCrawl . It can be imported directly via the SentenceTransformers package as shown below: The model can be downloaded from SentenceTransformer . The fine-tuneing and training processes were inspired by sbert's multilingual training techniques which are available here . The documentation shows and explains the step-by-step process of using parallel sentences to train models in a different language .,