Struct NGramTokenizer 

pub struct NGramTokenizer { /* private fields */ }

N-gram tokenizer for subword or character n-grams.

Implementations

impl NGramTokenizer

pub fn word_ngrams(n: usize) -> Self

Creates a word-level n-gram tokenizer.

pub fn char_ngrams(n: usize) -> Self

Creates a character-level n-gram tokenizer.

Trait Implementations

impl Clone for NGramTokenizer

fn clone(&self) -> NGramTokenizer

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for NGramTokenizer

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Tokenizer for NGramTokenizer

fn tokenize(&self, text: &str) -> Vec<String>

Tokenizes a string into tokens.

fn encode(&self, text: &str, vocab: &Vocab) -> Vec<usize>

Tokenizes and encodes to indices using a vocabulary.