Struct rust_tokenizers::tokenizer::MBart50Tokenizer

pub struct MBart50Tokenizer { /* fields omitted */ }

MBart50 tokenizer

MBart50 tokenizer performing:

• Splitting on language and special tokens
• text cleaning
• NFKC decomposition
• (optional) lower casing
• SentencePiece decomposition

Implementations

impl MBart50Tokenizer

pub fn from_file(
    path: &str,
    lower_case: bool
) -> Result<MBart50Tokenizer, TokenizerError>

Create a new instance of a MBart50Tokenizer Expects a SentencePiece protobuf file as an input.

Parameters

• path (&str): path to the SentencePiece model file
• lower_case (bool): flag indicating if the text should be lower-cased as part of the tokenization

Example

use rust_tokenizers::tokenizer::{MBart50Tokenizer, Tokenizer};
let lower_case = false;
let tokenizer = MBart50Tokenizer::from_file("path/to/vocab/file", lower_case).unwrap();

pub fn from_existing_vocab_and_model(
    vocab: MBart50Vocab,
    model: SentencePieceModel,
    lower_case: bool
) -> MBart50Tokenizer

Create a new instance of a MBart50Tokenizer from an existing vocabulary and model

Parameters

• vocab (MBart50Vocab): vocabulary
• model (SentencePieceModel): SentencePiece model
• lower_case (bool): flag indicating if the text should be lower-cased as part of the tokenization

Example

use rust_tokenizers::tokenizer::{MBart50Tokenizer, Tokenizer};
use rust_tokenizers::vocab::{MBart50Vocab, SentencePieceModel, Vocab};
let lower_case = false;
let vocab = MBart50Vocab::from_file("path/to/vocab/file").unwrap();
let model = SentencePieceModel::from_file("path/to/model/file").unwrap();

let tokenizer = MBart50Tokenizer::from_existing_vocab_and_model(vocab, model, lower_case);

Trait Implementations

impl MultiThreadedTokenizer<MBart50Vocab> for MBart50Tokenizer

fn vocab(&self) -> &T

returns a reference to the tokenizer vocabulary

fn tokenize_list_with_offsets<S>(
    &self,
    text_list: &[S]
) -> Vec<TokensWithOffsets> where
    S: AsRef<str> + Sync, 

Tokenize a list of strings (with multithreading), where each corresponds to for example a sentence, returns a vector of TokensWithOffsets containing the tokens and their offset information. This calls tokenize_with_offsets on the list provided.

fn tokenize_list<S>(&self, text_list: &[S]) -> Vec<Vec<String>> where
    S: AsRef<str> + Sync, 

Multithreaded tokenization of a list of strings, returning tokens with offset information

fn encode_list<S>(
    &self,
    text_list: &[S],
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput> where
    S: AsRef<str> + Sync, 

Multithreaded encoding of a sequence of string-like texts (tokenization followed by encoding). Not that in contrast with encode optional second text, each text provided is encoded independently.

fn encode_pair_list<S>(
    &self,
    text_list: &[(S, S)],
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput> where
    S: AsRef<str> + Sync, 

Multithreaded ncoding of a sequence of string-like text pairs (tokenization followed by encoding). This combines with encode with the list processing of encode_list.

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

Multithreaded conversion a list of sequence of ids (integer) into a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokenization spaces. This calls decode for each provided sequence of ids

impl Tokenizer<MBart50Vocab> for MBart50Tokenizer

fn vocab(&self) -> &MBart50Vocab

returns a reference to the tokenizer vocabulary

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

Tokenize a TokenRef, returning a sequence of tokens

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

Converts a sequence of strings into a single string. This will clean-up artifacts from tokenization (for example sub ##word) and generate a single output string

fn build_input_with_special_tokens(
    &self,
    tokens_ids_with_offsets_1: TokenIdsWithOffsets,
    tokens_ids_with_offsets_2: Option<TokenIdsWithOffsets>
) -> TokenIdsWithSpecialTokens

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens.

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 to return offset information.

fn tokenize_with_offsets(&self, text: &str) -> TokensWithOffsets

Tokenize a string, returning tokens with offset information

fn tokenize_list<S>(&self, text_list: &[S]) -> Vec<Vec<String>> where
    S: AsRef<str>, 

Tokenize a list of strings, returning tokens with offset information

fn tokenize_list_with_offsets<S>(
    &self,
    text_list: &[S]
) -> Vec<TokensWithOffsets> where
    S: AsRef<str>, 

Tokenize a list of strings, where each corresponds to for example a sentence, returns a vector of TokensWithOffsets containing the tokens and their offset information. This calls tokenize_with_offsets on the list provided.

fn convert_tokens_to_ids<S>(&self, tokens: &[S]) -> Vec<i64> where
    S: AsRef<str>, 

Convert a slice of string-like to a vector ot token indices

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

Encode a string-like (tokenization followed by encoding)

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

Encode a sequence of string-like texts (tokenization followed by encoding). Not that in contrast with encode optional second text, each text provided is encoded independently.

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

Encode a sequence of string-like text pairs (tokenization followed by encoding). This combines with encode with the list processing of encode_list.

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

Decode a sequence of token indices to a sequence of Strings, optionally skipping special indices

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

Converts a sequence of ids (integer) into a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokenization spaces.

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

Cleans-up tokenization artifacts (for example whitespace before punctuation)

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

Converts a list of sequence of ids (integer) into a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokenization spaces. This calls decode for each provided sequence of ids