Models and word lists served by whatname.app all-MiniLM-L6-v2 (Xenova/all-MiniLM-L6-v2@751bff37182d3f1213fa05d7196b954e230abad9), Apache License 2.0. Sentence-transformers model by Nils Reimers and contributors; ONNX conversion by Xenova. https://www.apache.org/licenses/LICENSE-2.0 Expansion vocabulary: whole words from the all-MiniLM-L6-v2 tokenizer (Apache License 2.0), filtered by the ESDB (SCOWL) en_US hunspell dictionary, used under the notice below. SmolLM2-360M-Instruct (HuggingFaceTB/SmolLM2-360M-Instruct@a10cc1512eabd3dde888204e902eca88bddb4951), Apache License 2.0. Not served by whatname.app: the small-LLM engine downloads it from Hugging Face when you ask it to. onnxruntime-web 1.31.0-dev.20260914-8d85527a0, MIT License, Copyright (c) Microsoft Corporation. Brand-name list (brand-names-*.txt): company and brand labels from Wikidata, CC0 1.0. https://creativecommons.org/publicdomain/zero/1.0/ Tiny model (tiny-small-*.onnx, tiny-large-*.onnx) and its known-name filter (tiny-known-*.bin): trained by WhatName on the brand-name list above (training/train.py). Translation table (translations-*.json): Latin, Italian, Spanish, Portuguese, French, Japanese, Finnish and Esperanto words for English vocabulary words, from Wikidata lexemes, CC0 1.0. No attribution is required; credited with thanks to the editors of Wikidata lexemes. Japanese readings romanised (Hepburn) by WhatName (scripts/build-translations.ts). https://creativecommons.org/publicdomain/zero/1.0/ ------------------------------------------------------------------------ ESDB (SCOWL) notice ------------------------------------------------------------------------ Copyright 2000-2026 by Kevin Atkinson Permission to use, copy, modify, distribute, and sell any part of the English Speller Database (ESDB, previously known as SCOWLv2), or word lists created from it, is hereby granted without fee, provided that the above copyright notice appears in all copies and that both the above copyright notice and this notice appear in supporting documentation. Kevin Atkinson makes no representations about the suitability of this database for any purpose. It is provided "as is" without express or implied warranty. ESDB is derived from many sources, most of which are in the Public Domain. Data from the Corpus of Contemporary American English (COCA) was also used. All data from COCA comes from 3-gram data that is not freely available; however, the usage is within the rights given by the NDA that was signed when purchasing the data. More information on COCA is available at https://www.english-corpora.org/coca/. The primary source of words for ESDB comes from 12dicts and ENABLE2K. Both are in the Public Domain, but Alan Beale deserves special credit as he is the author of 12dicts and a major contributor to ENABLE2K. In addition, he gave me an incredible amount of feedback and created a number of special lists in order to help improve the overall quality of ESDB.