Skip to content

custom tokenization #3

@bricksdont

Description

@bricksdont

vectorizer classes can take a custom tokenizer callable. Develop or use a tokenizer function for Swiss German / German mixed texts.

then words as features instead of char ngrams would make sense

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions