
Can neural networks transliterate Romaji into Japanese correctly?
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
179
+1 (Oct 13〜)
Last commit
Sep 2017
Created on GitHub
Jan 1, 2017
Listed
Aug 20, 2022
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | 178 |
| Jan 2026 | 178 |
| Feb 2026 | 178 |
| Mar 2026 | 178 |
| Apr 2026 | 178 |
| May 2026 | — |
| Jun 2026 | 178 |
| Jul 2026 | 178 |
| Aug 2026 | 178 |
| Sep 2026 | 178 |
| Oct 2026 | 179 |
| Nov 2026 | 179 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
yomiyasunanaism3.3kAI生成の日本語を自然な日本語へ推敲するAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese
mozc-devicesgoogle3kAutomatically exported from code.google.com/p/mozc-morse
manga-ocrkha-white2.8kAbout Optical character recognition for Japanese text, with the main focus being Japanese manga
natural-japanesecoji2.1kThis is an Agent Skill for writing and correcting work-related Japanese in an easy-to-read and easy-to-understand manner.
voicevox_engineVOICEVOX1.8kVOICEVOX is a high-quality text-to-speech software that can be used for free.
mokurokha-white1.8kRead Japanese manga inside browser with selectable text.
Resources in similar research fields
- japanese-hubert-baseyky-h28kJapanese HuBERT Base, a 12‑layer transformer mirroring rinna’s original, trained on ~19,000 hrs of ReazonSpeech v1 Japanese speech and released under the Apache 2.0 license.HF modelShared: Representation Learning
- sarashina-embedding-v2-1bsbintuitions2kSarashina‑Embedding‑v2‑1B is a 1,792‑dimensional Japanese sentence transformer trained with multi‑stage contrastive learning that achieves state‑of‑the‑art JMTEB scores, and can be used for semantic similarity, search, paraphrase mining, classification, and clustering via Sentence‑Transformers with optional instruction prefixes.HF modelShared: Representation Learning
- clip-japanese-base-v2line-corporation2kJapanese CLIP model clip‑japanese‑base‑v2, upgraded with ~2 B image‑text pairs and distillation, pairs an Eva02‑B image encoder with a 12‑layer BERT text encoder to reach higher ImageNet‑1k accuracy (0.708) than its predecessor.HF modelShared: Representation Learning
albert-japanese-tinysegmenternknytk13Pretrained models, codes and guidances to pretrain official ALBERT(https://github.com/google-research/albert) on Japanese Wikipedia ResourcesShared: Representation Learning・Text Generation- sup-simcse-ja-basecl-nagoya2kA Japanese BERT‑base model fine‑tuned with supervised SimCSE on JSNLI, exposed via Sentence‑Transformers or HuggingFace with CLS pooling, trained on 1 M examples at 512‑batch size, 5 × 10⁻⁵ learning rate, 5 × 10⁻⁵ temperature, 64‑token limit, and BFloat16 precision.HF modelShared: Representation Learning
- wav2vec2-large-xlsr-53-japanesejonatasgrosman16MJapanese wav2vec‑2 XLSR‑53 fine‑tuned on Common Voice 6.1, CSS10, and JSUT, requiring 16 kHz audio and usable via HuggingSound or HuggingFace pipelines.HF modelShared: Representation Learning・Text Generation