CharTokenizer

public final class CharTokenizer implements Tokenizer

A Character Tokenizer which returns a token for each character in the string.

Constructors

Link copied to clipboard
public CharTokenizer CharTokenizer()

Functions

Link copied to clipboard
public List<List<String>> batchSplit(List<String> texts)

A more efficient approach for native tokenizers, i.e. HuggingFaceTokenizer

Link copied to clipboard
public List<String> split(String text)