✎ Edit this page

Japanese

Japanese is the language of Japanese Buddhism and of a large body of Buddhist scholarship. Japanese Buddhists also read the Chinese canon as kanbun. Short answer: current AI models translate well into modern Japanese. For kanbun, they give the meaning but are weak at the traditional Japanese reading order.

Summary

   
Where Japan and the diaspora
Speakers about 126 million in total (Ethnologue 2026) [1]
Script Kanji, hiragana, katakana
AI resources high
Google Translate yes, Translation LLM and NMT [2]
Microsoft Translator yes, with LLM translation [3]
Speech to text yes; Whisper large-v3 WER 4.8 on FLEURS [10]
Best evidence on translation quality WMT24 human evaluation (2024) [7]; WMT25 automatic ranking (2025) [8]

Writing and text input

Unicode, fonts and input are mature. Japanese has no spaces between words.

OCR for premodern Japanese books is mature. NDL Kotenseki OCR (National Diet Library, v3.0) reaches about 92% average accuracy, as reported by its developers. It is called open source, but the license was not named. Its errors often look plausible, so they are hard to catch. Kanbun with reading marks was not discussed [13]. Google Research published “miwo”, a kuzushiji recognition app [14]. SAT added 329 Taishō characters to Unicode 13.0 in 2020 [15].

Data

Speech

Machine translation

Benchmark, WMT24, English to Japanese, human scores (higher is better), 2024 [7]: human reference 91.8; ONLINE-B 91.1; CommandR-plus 91.0; Claude-3.5-Sonnet 90.8; GPT-4 90.8; Gemini-1.5-Pro 90.0.

Benchmark, WMT25 preliminary automatic ranking, English to Japanese (lower is better), 2025 [8]: Shy-hunyuan-MT 1.0, In2x 2.3, Gemini-2.5-Pro 2.4, GPT-4.1 2.9, DeepSeek-V3 4.6, Claude-4 5.7. Human evaluation replaces these.

Benchmark, FLORES-200, English to Japanese, chrF++ (higher is better): NLLB about 25.2 [4]; in 2023, ChatGPT 5-shot 33.7 and Google Translate 37.1 [5]. These scores are low partly because chrF++ counts characters. chrF++ cannot be compared across languages.

Vendor claim: Claude models score 97.4–99.5% of their English score on Global-MMLU in Japanese. This tests knowledge, not translation [6].

All results are general text. We found no Buddhist test into Japanese. Older results may not show what current models can do.

Classical form: kanbun

Kanbun is Classical Chinese read in Japanese order with marks (kundoku).

AI projects

Recommendation

In the Directory

Projects and datasets in the Directory that list Japanese. This list is made from the Directory data. To add an entry, suggest it.

Projects (2)

Datasets (2)

Sources

  1. Wikipedia: List of languages by total number of speakers (Ethnologue 2026), read 2026-11-17
  2. Google Cloud Translation: Language support, read 2026-11-17
  3. Microsoft Learn: Translator language support, read 2026-11-17
  4. NLLB metrics, public copy (Mara4444/MSc_Thesis), read 2026-11-17
  5. Robinson et al. 2023, ChatGPT MT, arXiv 2309.07423, read 2026-11-17
  6. Claude docs: Multilingual support, read 2026-11-17
  7. WMT24 Findings, read 2026-11-17
  8. WMT25 preliminary ranking, arXiv 2508.14909, read 2026-11-17
  9. Swallow leaderboard, about page, read 2026-11-17
  10. Dolphin paper, arXiv 2503.20212, read 2026-11-17
  11. Omnilingual ASR per-language results (7B LLM-ASR), read 2026-11-17
  12. openai/whisper tokenizer.py, read 2026-11-17
  13. Digital Orientalist: Overview of NDL Kotenseki OCR, 2026-02-24, read 2026-11-17
  14. Google Research: miwo, read 2026-11-17
  15. SAT Daizōkyō Text Database, read 2026-11-17
  16. Kanbun-LM, arXiv 2305.12759, read 2026-11-17
  17. Li and Cao, KanbunKundoku, arXiv 2511.05239, read 2026-11-17
  18. Song et al., arXiv 2411.04822, read 2026-11-17
  19. Adnkronos/Jiji: Japanese group develops Buddhist AI humanoid robot, 2026-06-25, read 2026-11-17
  20. CBETA Copyright Notice, read 2026-11-17

✎ Edit this page · History · Discuss