A curated dataset of human‑approved Japanese sentences paired with accurate katakana readings to evaluate and improve Beam’s pronunciation corrections, covering numbers, units, symbols, context‑dependent words, proper nouns, medical terms, and emergency broadcast style text.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
155
Hugging Face likes
2
Listed
Nov 3, 2026
Popular in the same category
- emilia-yodasTTS-AGI18kDataset of dialogues and lore from the Fate/Stay Night character “Emilia”, formatted for training and evaluating conversational language models.
- fgo_voices_jpdeepghs10kJP Voice‑Text Dataset for FGO Waifus: a 30,800‑record, 66.4‑hour Japanese audio collection of single‑voice‑actor character lines (≈7.76 s each) useful for ASR/ASV fine‑tuning and evaluation.
- JGLUEshunk0313kUpdated JGLUE dataset card and loading script for a Japanese NLP benchmark (created by Yahoo Japan and Waseda University) that covers text classification (MARC‑ja, JCoLA), sentence‑pair classification (JNLI), and QA (JSQuAD, JCommonsenseQA), with releases linked on GitHub and Hugging Face.
- JMTEBsbintuitions3kJMTEB is a Japanese text‑embedding benchmark featuring 5 tasks (clustering, classification, STS, retrieval, reranking) and 28 datasets, offering a one‑line evaluation script and inviting community contributions.
- JMMMUJMMMU3kJMMMU is a Japanese multimodal benchmark expanded over tenfold to 1,320 culturally diverse questions (720 culture‑agnostic, 600 culture‑specific) translated by native subject experts, now featuring a public leaderboard.
- JamC-QAsbintuitions2kJamC‑QA is a bilingual benchmark of multiple‑choice questions spanning eight Japanese‑culture and knowledge categories, with leaderboard metrics comparing state‑of‑the‑art models.
Resources in similar research fields
lm-evaluation-harnessEleutherAI14kA framework for few-shot evaluation of language models.MultilingualShared: Corpora & datasets・Evaluation & benchmarks- ELYZA-tasks-100elyza2kA 100‑sample Japanese instruction‑tuning evaluation dataset of annotated tasks—ranging from summarization correction and math reasoning to translation, creative generation, and user‑intent understanding—designed for manual or automatic 5‑point rating of fine‑tuned models.Shared: Corpora & datasets・Evaluation & benchmarks
- JMMLUnlp-waseda1kJMMLU is a Japanese Massive Multitask Language Understanding Benchmark featuring 7,536 teacher‑crafted questions across 56 subjects, including professional medicine, psychology, accounting, philosophy, and diverse high‑school disciplines.Shared: Corpora & datasets・Evaluation & benchmarks
sacrebleumjpost1.3kReference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons.MultilingualShared: Corpora & datasets・Evaluation & benchmarks
xtremegoogle-research650XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.MultilingualShared: Corpora & datasets・Evaluation & benchmarks
pawsgoogle-research-datasets572This dataset contains 108,463 human-labeled and 656k noisily labeled pairs that feature the importance of modeling structure, context, and word order information for the problem of paraphrase identification.MultilingualShared: Corpora & datasets・Evaluation & benchmarks