| { | |
| "model_name": "trankit decompressed weights", | |
| "version": "1.0.0", | |
| "library_name": "trankit", | |
| "source": "https://github.com/nlp-uoregon/trankit", | |
| "license": "apache-2.0", | |
| "architectures": [ | |
| "xlm-roberta-base", | |
| "xlm-roberta-large" | |
| ], | |
| "tasks": [ | |
| "tokenization", | |
| "pos-tagging", | |
| "dependency-parsing", | |
| "named-entity-recognition", | |
| "lemmatization" | |
| ], | |
| "languages": [ | |
| "afrikaans", | |
| "ancient-greek", | |
| "ancient-greek-perseus", | |
| "arabic", | |
| "armenian", | |
| "basque", | |
| "belarusian", | |
| "bulgarian", | |
| "catalan", | |
| "chinese", | |
| "classical-chinese", | |
| "croatian", | |
| "czech", | |
| "czech-cac", | |
| "czech-cltt", | |
| "czech-fictree", | |
| "danish", | |
| "dutch", | |
| "dutch-lassysmall", | |
| "english", | |
| "english-gum", | |
| "english-lines", | |
| "english-partut", | |
| "estonian", | |
| "estonian-ewt", | |
| "finnish", | |
| "finnish-ftb", | |
| "french", | |
| "french-partut", | |
| "french-sequoia", | |
| "french-spoken", | |
| "galician", | |
| "galician-treegal", | |
| "german", | |
| "german-hdt", | |
| "greek", | |
| "hebrew", | |
| "hindi", | |
| "hungarian", | |
| "indonesian", | |
| "irish", | |
| "italian", | |
| "italian-partut", | |
| "italian-postwita", | |
| "italian-twittiro", | |
| "italian-vit", | |
| "japanese", | |
| "kazakh", | |
| "korean", | |
| "korean-kaist", | |
| "kurmanji", | |
| "latin", | |
| "latin-perseus", | |
| "latin-proiel", | |
| "latvian", | |
| "lithuanian", | |
| "lithuanian-hse", | |
| "marathi", | |
| "norwegian-bokmaal", | |
| "norwegian-nynorsk", | |
| "norwegian-nynorsklia", | |
| "old-french", | |
| "old-russian", | |
| "persian", | |
| "polish", | |
| "polish-lfg", | |
| "portuguese", | |
| "portuguese-gsd", | |
| "romanian", | |
| "romanian-nonstandard", | |
| "russian", | |
| "russian-gsd", | |
| "russian-taiga", | |
| "scottish-gaelic", | |
| "serbian", | |
| "slovak", | |
| "slovenian", | |
| "slovenian-sst", | |
| "spanish", | |
| "spanish-gsd", | |
| "swedish", | |
| "swedish-lines", | |
| "tamil", | |
| "telugu", | |
| "traditional-chinese", | |
| "turkish", | |
| "ukrainian", | |
| "urdu", | |
| "uyghur", | |
| "vietnamese", | |
| "vietnamese-vtb" | |
| ], | |
| "notes": "All files were extracted from uonlp/trankit so that downstream users can download ready-to-use weights without zip archives." | |
| } | |