Struct CharTokenizer 

pub struct CharTokenizer { /* private fields */ }

Character-level tokenizer (simple baseline)

Implementations

impl CharTokenizer

pub fn new(config: TokenizerConfig) -> Self

Create a new character tokenizer

Trait Implementations

impl Clone for CharTokenizer

fn clone(&self) -> CharTokenizer

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CharTokenizer

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for CharTokenizer

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for CharTokenizer

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Tokenizer for CharTokenizer

fn train(&mut self, corpus: &[&str]) -> Result<()>

Train the tokenizer on a corpus

fn encode(&self, text: &str) -> Result<Vec<TokenId>>

Encode text to token IDs

fn decode(&self, ids: &[TokenId]) -> Result<String>

Decode token IDs to text

fn vocab_size(&self) -> usize

Get vocabulary size

fn is_trained(&self) -> bool

Check if tokenizer is trained

fn id_to_token(&self, _id: TokenId) -> Option<&str>

Get token for ID

fn token_to_id(&self, token: &str) -> Option<TokenId>

Get ID for token