Struct rust_tokenizers::preprocessing::tokenizer::marian_tokenizer::MarianTokenizer

pub struct MarianTokenizer { /* fields omitted */ }

Implementations

impl MarianTokenizer

pub fn from_files(
    vocab_path: &str,
    model_path: &str,
    lower_case: bool
) -> MarianTokenizer

pub fn from_existing_vocab_and_model(
    vocab: MarianVocab,
    model: SentencePieceModel,
    lower_case: bool
) -> MarianTokenizer

Trait Implementations

impl MultiThreadedTokenizer<MarianVocab> for MarianTokenizer

fn vocab(&self) -> &T

fn tokenize_list_with_offsets(
    &self,
    text_list: Vec<&str>
) -> Vec<(Vec<String>, Vec<Option<Offset>>, Vec<Vec<OffsetSize>>, Vec<Mask>)>

fn tokenize_list(&self, text_list: Vec<&str>) -> Vec<Vec<String>>

fn encode_list(
    &self,
    text_list: Vec<&str>,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput>

fn encode_pair_list(
    &self,
    text_list: Vec<(&str, &str)>,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput>

fn decode_list(
    &self,
    token_ids_list: Vec<Vec<i64>>,
    skip_special_tokens: bool,
    clean_up_tokenization_spaces: bool
) -> Vec<String>

impl Tokenizer<MarianVocab> for MarianTokenizer

fn vocab(&self) -> &MarianVocab

fn tokenize_to_tokens(&self, text: TokenRef) -> Vec<Token>

Tokenize a text, returns a vector of tokens (contains offset information and more)

fn convert_tokens_to_string(&self, tokens: Vec<String>) -> String

fn build_input_with_special_tokens(
    &self,
    tokens_1: Vec<i64>,
    tokens_2: Option<Vec<i64>>,
    offsets_1: Vec<Option<Offset>>,
    offsets_2: Option<Vec<Option<Offset>>>,
    original_offsets_1: Vec<Vec<OffsetSize>>,
    original_offsets_2: Option<Vec<Vec<OffsetSize>>>,
    mask_1: Vec<Mask>,
    mask_2: Option<Vec<Mask>>
) -> (Vec<i64>, Vec<i8>, Vec<i8>, Vec<Option<Offset>>, Vec<Vec<OffsetSize>>, Vec<Mask>)

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A RoBERTa sequence has the following format: single sequence: X pair of sequences: A B

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

Tokenize a string, returns a vector of tokens as strings. Use tokenize_with_offsets or tokenize_to_tokens if you also want offset information.

fn tokenize_with_offsets(
    &self,
    text: &str
) -> (Vec<String>, Vec<Option<Offset>>, Vec<Vec<OffsetSize>>, Vec<Mask>)

Tokenize a string, return offset information

fn tokenize_list(&self, text_list: Vec<&str>) -> Vec<Vec<String>>

Tokenize a vector of strings, where each corresponds to for example a sentence, returns a vector of vectors of strings. Use tokenize_list_with_offsets if you also want offset information.

fn tokenize_list_with_offsets(
    &self,
    text_list: Vec<&str>
) -> Vec<(Vec<String>, Vec<Option<Offset>>, Vec<Vec<OffsetSize>>, Vec<Mask>)>

Tokenize a vector of strings, where each corresponds to for example a sentence, returns a vector of pairs consists of a vector of tokens and a list of offset information.

fn convert_tokens_to_ids(&self, tokens: &Vec<String>) -> Vec<i64>

fn encode(
    &self,
    text_1: &str,
    text_2: Option<&str>,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> TokenizedInput

fn encode_list(
    &self,
    text_list: Vec<&str>,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput>

fn encode_pair_list(
    &self,
    text_list: Vec<(&str, &str)>,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput>

fn decode_to_vec(
    &self,
    token_ids: Vec<i64>,
    skip_special_tokens: bool
) -> Vec<String>

fn decode(
    &self,
    token_ids: Vec<i64>,
    skip_special_tokens: bool,
    clean_up_tokenization_spaces: bool
) -> String

Converts a sequence of ids (integer) into astring, using the tokenizer and vocabulary with options to remove special tokens and clean up tokenization spaces. Args: * token_ids: list of tokenized input ids. Can be obtained using the encode or encode_plus methods. * skip_special_tokens: if set to True, will replace special tokens. * clean_up_tokenization_spaces: if set to True, will clean up the tokenization spaces.

fn clean_up_tokenization(&self, input_string: String) -> String

fn decode_list(
    &self,
    token_ids_list: Vec<Vec<i64>>,
    skip_special_tokens: bool,
    clean_up_tokenization_spaces: bool
) -> Vec<String>