Module tokenizers::models::unigram

source ·
Expand description

Unigram model.

Structs§

  • Structure to implement Viterbi algorithm to find the best encoding, or sample from all possible encodings of a given sentence.
  • A node from the lattice, that helps reconstruct the underlying String
  • A Unigram model to encode sentences.
  • Iterator to iterate of vocabulary of the model, and their relative score.
  • A UnigramTrainer can train a Unigram model from word_counts.
  • Builder for UnigramTrainer.

Enums§