HF model

tohoku-nlp / bert-base-japanese-char-whole-word-masking

A 12‑layer, 768‑dimensional BERT‑Base Japanese model trained on 2.6 GB of Wikipedia (≈17 M sentences), using IPA‑dictionary character tokenisation with whole‑word masking, and released under CC‑BY‑SA 3.0.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
1,000
Hugging Face likes
4
Listed
May 13, 2024

Downloads (30-day window) over time

1k1.5k2kNovSepJulMayMarJan 20261,000
Show as a table
MonthDL (30d)
Dec 2025—
Jan 2026—
Feb 20261,000
Mar 20261,000
Apr 20262,000
May 20261,000
Jun 2026—
Jul 20261,000
Aug 20261,000
Sep 20261,000
Oct 20261,000
Nov 20261,000

Downloads over the 30 days before the last snapshot of each month.

Popular in the same category

Resources in similar research fields

Learn from slides & articles