audio2vec 3 image2vec 3 bpe 1 cooccurrence 1 embeddings 1 latent-dirichlet-allocation 1 matrix 1 minhash-lsh-algorithm 1 mutual-information 1 ngram-language-model 1 tokenization 1 tokenizer 1 vocabulary-builder 1 word2vec 1 word2word-matrix 1 wordgrams 1 wordpeice 1 wordpiece-tokenization 1 bayesian-inference 1 word2vec-model 1 word2vec-embeddinngs 1 vectorization 1 skipgram 1 nlp-embeddings 1 input-embeddings 1 image-vectorization 1 glove-vectors 1 glove-embeddings 1 fasttext-embeddings 1 cbow-embeddings 1 audio-vectorization 1 vector-database 1 image-to-vector 1 audio-to-vector 1