Directory
Published directory entries matching your search.
DeepL Language Translator is a translation service that provides instant text and full document translation. It also offers real-time voice translation, writing enhancement tools, an API for building multilingual experiences, and integrations with productivity software. The service is used by over 200,000 businesses globally, alongside individual users.
Digital Library of India is a non-English reading, font, dictionary, or language-learning resource.
dohadictionary is a non-English reading, font, dictionary, or language-learning resource.
DPAN is a deaf-led 501(c)(3) nonprofit multimedia production company that operates DPAN.TV, a sign language channel. It produces American Sign Language (ASL)-centric content including video productions, ASL captions and transcripts, media dubbing, audio work, ASL data collection solutions, and educational projects such as the PopSign ASL learning game. It has partnered with PBS on projects related to the Americans with Disabilities Act.
EBook Land is a non-English reading, font, dictionary, or language-learning resource.
eBookForum is a non-English reading, font, dictionary, or language-learning resource.
eBooksBrasil is a non-English reading, font, dictionary, or language-learning resource.
Facebook is a non-English reading, font, dictionary, or language-learning resource.
Facebook is a non-English reading, font, dictionary, or language-learning resource.
Facebook is a non-English reading, font, dictionary, or language-learning resource.
FoLiA is an XML-based format for linguistic annotation intended for representing and exchanging written language resources such as corpora. It aims to accommodate many annotation types through a generalized paradigm without committing to a particular label set, language or linguistic theory. The project includes documentation, a RelaxNG schema and software libraries.
FoulaBook is a non-English reading, font, dictionary, or language-learning resource.
Honto is a non-English reading, font, dictionary, or language-learning resource.
A blog guide on FinetuneDB covering best practices for evaluating Large Language Model outputs. It explains what LLM output evaluation is, why it matters, and describes evaluation datasets, model-based judgments and human judgments as approaches for structuring the process.
IndianSignLanguage is a non-English reading, font, dictionary, or language-learning resource.
IndonesiaEbook is a non-English reading, font, dictionary, or language-learning resource.
J2team is a non-English reading, font, dictionary, or language-learning resource.
KoNLPy (pronounced "ko en el PIE") is a Python package for natural language processing of the Korean language. It is open source software released under GPL v3 or above, and users are asked to acknowledge its use with a citation.
LifeArchitect.ai hosts a Models Table of large language model data, including parameters, tokens trained, and benchmark scores such as MMLU, MMLU-Pro, GPQA and HLE. The page also presents rankings, a data dictionary and visualization snapshots of frontier models.
LMQL is a programming language for interacting with large language models, using types, templates, constraints and an optimizing runtime. Prompt statements have associated where clauses that specify logical constraints on output, which LMQL translates to subtoken masks enforced during generation. It works across llama.cpp, OpenAI and Transformers backends and supports nested queries.
MathArena evaluates large language models on uncontaminated math benchmarks. It presents model analysis across competitions such as ArXivLean, BrokenArXiv, ArXivMath, Visual Math, Final-Answer Comps, Proof-Based Comps and Project Euler. A competition is selected to load tables and a leaderboard, and clicking a cell shows the raw model output.
mp3-book is a non-English reading, font, dictionary, or language-learning resource.
Native Land is a resource and app for learning about Indigenous territories, languages, lands, and ways of life, and for mapping Indigenous territories, treaties, and languages. It also states that its maps are not official sources. The site notes it provides geoJSONs and an API for free.
Noor Book is a non-English reading, font, dictionary, or language-learning resource.
