Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need
Installs just this skill. Get the whole plugin for auto-invocation.
⚡ How it fires
How this skill gets triggered: by you, by Claude, or both.
Fires itselfClaude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/tokenization-sentencepiece
👁️ Context preview
The summary Claude sees to decide when to auto-load this skill.
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need
📊 Stats
Stars29,853
Forks3,189
LanguagePython
LicenseMIT
📦 Ships with claude-code-templates
</> SKILL.md
tokenization-sentencepiece.SKILL.md
---name: sentencepiece
description: Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Tokenization, SentencePiece, Language-Independent, BPE, Unigram, Multilingual, CJK Languages, Unicode, Deterministic, Google]
dependencies: [sentencepiece, transformers]
---# SentencePiece - Language-Independent Tokenization
Unsupervised tokenizer that works on raw text without language-specific preprocessing.
## When to use SentencePiece
**Use SentencePiece when:**
- Building multilingual models (no language-specific rules)
- Working with CJK languages (Chinese, Japanese, Korean)
- Need reproducible tokenization (deterministic vocabulary)
- Want to train on raw text (no pre-tokenization needed)
- Require lightweight deployment (6MB memory, 50k sentences/sec)
**Performance**:
- **Speed**: 50,000 sentences/sec
- **Memory**: ~6MB for loaded model
