Instructions to use LynLab/yomigana-bert-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LynLab/yomigana-bert-test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="LynLab/yomigana-bert-test")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("LynLab/yomigana-bert-test") model = AutoModelForTokenClassification.from_pretrained("LynLab/yomigana-bert-test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
yomigana-bert-test (LynLab test01)
文脈依存の同形異音語(20語・40読み)について、TTS前処理向けに正しい読みを token 分類で予測するテストモデル。 テンプレート生成データで学習し、未見テンプレートで評価した、パイプライン検証用のテストモデルです。本番版は実データで学習し、別途公開予定です。
Eval (template-held-out, n=90)
- model: 0.767
- pykakasi baseline: 0.444
- MeCab(UniDic) baseline: 0.522
Base: tohoku-nlp/bert-base-japanese-v3
- Downloads last month
- 4