Struct rust_tokenizers::tokenizer::MBart50Tokenizer [−][src]
pub struct MBart50Tokenizer { /* fields omitted */ }
Expand description
MBart50 tokenizer
MBart50 tokenizer performing:
- Splitting on special tokens
- text cleaning
- NFKC decomposition
- (optional) lower casing
- SentencePiece decomposition
Implementations
Create a new instance of a MBart50Tokenizer
Expects a json vocab file and 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::{Tokenizer, MBart50Tokenizer}; 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
[src]
pub fn from_existing_vocab_and_model(
vocab: MBart50Vocab,
model: SentencePieceModel,
lower_case: bool
) -> MBart50Tokenizer
[src]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::{Tokenizer, MBart50Tokenizer}; use rust_tokenizers::vocab::{SentencePieceModel, Vocab, MBart50Vocab}; 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
fn tokenize_list_with_offsets<S, ST>(
&self,
text_list: S
) -> Vec<TokensWithOffsets> where
S: AsRef<[ST]>,
ST: AsRef<str> + Sync,
[src]
fn tokenize_list_with_offsets<S, ST>(
&self,
text_list: S
) -> Vec<TokensWithOffsets> where
S: AsRef<[ST]>,
ST: AsRef<str> + Sync,
[src]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. Read more
Multithreaded tokenization of a list of strings, returning tokens with offset information Read more
fn encode_list<S, ST>(
&self,
text_list: S,
max_len: usize,
truncation_strategy: &TruncationStrategy,
stride: usize
) -> Vec<TokenizedInput> where
S: AsRef<[ST]>,
ST: AsRef<str> + Sync,
[src]
fn encode_list<S, ST>(
&self,
text_list: S,
max_len: usize,
truncation_strategy: &TruncationStrategy,
stride: usize
) -> Vec<TokenizedInput> where
S: AsRef<[ST]>,
ST: AsRef<str> + Sync,
[src]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. Read more
fn encode_pair_list<S, ST>(
&self,
text_list: S,
max_len: usize,
truncation_strategy: &TruncationStrategy,
stride: usize
) -> Vec<TokenizedInput> where
S: AsRef<[(ST, ST)]>,
ST: AsRef<str> + Sync,
[src]
fn encode_pair_list<S, ST>(
&self,
text_list: S,
max_len: usize,
truncation_strategy: &TruncationStrategy,
stride: usize
) -> Vec<TokenizedInput> where
S: AsRef<[(ST, ST)]>,
ST: AsRef<str> + Sync,
[src]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
. Read more
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 Read more
returns a reference to the tokenizer vocabulary
Tokenize a TokenRef, returning a sequence of tokens Read more
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 Read more
fn build_input_with_special_tokens(
&self,
tokens_ids_with_offsets_1: TokenIdsWithOffsets,
tokens_ids_with_offsets_2: Option<TokenIdsWithOffsets>
) -> TokenIdsWithSpecialTokens
[src]
fn build_input_with_special_tokens(
&self,
tokens_ids_with_offsets_1: TokenIdsWithOffsets,
tokens_ids_with_offsets_2: Option<TokenIdsWithOffsets>
) -> TokenIdsWithSpecialTokens
[src]Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. Read more
Tokenize a string, returns a vector of tokens as strings.
Use tokenize_with_offsets
or tokenize_to_tokens
to return offset information. Read more
Tokenize a string, returning tokens with offset information Read more
Tokenize a list of strings, returning tokens with offset information Read more
fn tokenize_list_with_offsets<S, ST>(
&self,
text_list: S
) -> Vec<TokensWithOffsets> where
S: AsRef<[ST]>,
ST: AsRef<str>,
[src]
fn tokenize_list_with_offsets<S, ST>(
&self,
text_list: S
) -> Vec<TokensWithOffsets> where
S: AsRef<[ST]>,
ST: AsRef<str>,
[src]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. Read more
Convert a slice of string-like to a vector ot token indices Read more
fn encode<S: AsRef<str>>(
&self,
text_1: S,
text_2: Option<S>,
max_len: usize,
truncation_strategy: &TruncationStrategy,
stride: usize
) -> TokenizedInput
[src]
fn encode<S: AsRef<str>>(
&self,
text_1: S,
text_2: Option<S>,
max_len: usize,
truncation_strategy: &TruncationStrategy,
stride: usize
) -> TokenizedInput
[src]Encode a string-like (tokenization followed by encoding) Read more
fn encode_list<S, ST>(
&self,
text_list: S,
max_len: usize,
truncation_strategy: &TruncationStrategy,
stride: usize
) -> Vec<TokenizedInput> where
S: AsRef<[ST]>,
ST: AsRef<str>,
[src]
fn encode_list<S, ST>(
&self,
text_list: S,
max_len: usize,
truncation_strategy: &TruncationStrategy,
stride: usize
) -> Vec<TokenizedInput> where
S: AsRef<[ST]>,
ST: AsRef<str>,
[src]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. Read more
fn encode_pair_list<S, ST>(
&self,
text_list: S,
max_len: usize,
truncation_strategy: &TruncationStrategy,
stride: usize
) -> Vec<TokenizedInput> where
S: AsRef<[(ST, ST)]>,
ST: AsRef<str>,
[src]
fn encode_pair_list<S, ST>(
&self,
text_list: S,
max_len: usize,
truncation_strategy: &TruncationStrategy,
stride: usize
) -> Vec<TokenizedInput> where
S: AsRef<[(ST, ST)]>,
ST: AsRef<str>,
[src]Encode a sequence of string-like text pairs (tokenization followed by encoding). This combines
with encode
with the list processing of encode_list
. Read more
Decode a sequence of token indices to a sequence of Strings, optionally skipping special indices Read more
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. Read more
Cleans-up tokenization artifacts (for example whitespace before punctuation) Read more
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 Read more
Auto Trait Implementations
impl RefUnwindSafe for MBart50Tokenizer
impl Send for MBart50Tokenizer
impl Sync for MBart50Tokenizer
impl Unpin for MBart50Tokenizer
impl UnwindSafe for MBart50Tokenizer