splintr 0.18.0

Fast Rust tokenizer (BPE + SentencePiece + WordPiece) with Python bindings
Documentation
1
2
3
4
5
6
7
mod bindings;

pub use bindings::{
    base_vocab_size, from_json, from_json_bytes, register_agent_tokens, PyAnyTokenizer,
    PySentencePieceTokenizer, PySpmTokenizer, PyStreamingDecoder, PyTokenizer,
    PyWordPieceTokenizer,
};