
A repository of Japanese Phoneme-Level BERT
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
24
±0 (Oct 13〜)
Last commit
Dec 2023
Created on GitHub
Jun 9, 2023
Listed
Dec 30, 2025
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | 22 |
| Jan 2026 | 22 |
| Feb 2026 | 22 |
| Mar 2026 | 24 |
| Apr 2026 | 24 |
| May 2026 | 24 |
| Jun 2026 | 24 |
| Jul 2026 | 24 |
| Aug 2026 | 24 |
| Sep 2026 | 24 |
| Oct 2026 | 24 |
| Nov 2026 | 24 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
JGLUEyahoojapan349JGLUE: Japanese General Language Understanding Evaluation
llm-jp-evalllm-jp175This tool is designed to automatically evaluate large-scale Japanese language models across multiple datasets.
jp-stabletree155JP Language Model Evaluation Harness
llm-lora-classificationhppRC97llm-lora-classification
japanese-lm-fin-harnesspfnet-research80Japanese Language Model Financial Evaluation Harness
llm-jp-sftllm-jp66This repository contains the code for supervised fine-tuning of LLM-jp models.
Resources in similar research fields
pretrained_doc2vec_jayagays25pretrained doc2vec models on Japanese WikipediaShared: Language Models
swallow-evaluation-instructswallow-llm34Swallow Project Post-learning Large-scale Language Model Evaluation FrameworkShared: Language Models- modernbert-ja-310msbintuitions36kModernBERT‑Ja‑310M is a Japanese‑language BERT variant that blends local‑global attention with RoPE, trained on 4.09 T tokens of Japanese/English text, supports a 102 400‑word vocabulary, 8 192‑token sequences, and is optimized for Flash Attention 2.HF modelShared: Language Models
- deberta-v2-base-japanese-char-wwmku-nlp24kA Japanese DeBERTa‑V2 base model pre‑trained on 171 GB of Japanese Wikipedia, CC‑100, and OSCAR text with character‑level tokenization, whole‑word masking, trained for 20 days on 8 A100 GPUs, and ready for downstream fine‑tuning.HF modelShared: Language Models
- deberta-v2-base-japaneseku-nlp24kJapanese DeBERTa V2 base model pretrained on 171 GB of Japanese Wikipedia, CC‑100 and OSCAR data using Juman++ segmentation and SentencePiece tokenization, trained for three weeks on eight NVIDIA A100 GPUs and ready for fine‑tuning.HF modelShared: Language Models
- modernbert-ja-130msbintuitions12kA 132‑million‑parameter Japanese ModernBERT model that blends local‑global and RoPE attention, trained on 4.39 T tokens (Japanese/English) with a 102‑k‑size vocab, 8,192‑token max length, and optimized for Flash Attention 2.HF modelShared: Language Models