spaCy/website/models/_data.json

{
    "sidebar": {
        "Models": {
            "Overview": "./",
            "Comparison": "comparison"
        },

        "Language models": {
            "English": "en",
            "German": "de",
            "Spanish": "es",
            "Portuguese": "pt",
            "French": "fr",
            "Italian": "it",
            "Dutch": "nl",
            "Multi-Language": "xx"
        }
    },

    "index": {
        "title": "Models Overview",
        "teaser": "Downloadable statistical models for spaCy to predict and assign linguistic features.",
        "quickstart": true,
        "menu": {
            "Quickstart": "quickstart",
            "Installation": "install",
            "Naming Conventions": "conventions"
        }
    },

    "comparison": {
        "title": "Model Comparison",
        "teaser": "Compare spaCy's statistical models and their accuracy.",
        "tag": "experimental",
        "compare_models": true,
        "default_models": {
            "model1": "en_core_web_sm",
            "model2": "en_core_web_lg"
        }
    },

    "MODELS": {
        "en": ["en_core_web_sm", "en_core_web_lg", "en_vectors_web_lg"],
        "de": ["de_core_news_sm"],
        "es": ["es_core_news_sm", "es_core_news_md"],
        "pt": ["pt_core_news_sm"],
        "fr": ["fr_core_news_sm"],
        "it": ["it_core_news_sm"],
        "xx": ["xx_ent_wiki_sm"]
    },

    "MODEL_META": {
        "core": "Vocabulary, syntax, entities, vectors",
        "dep": "Vocabulary, syntax",
        "ent": "Named entities",
        "vectors": "Word vectors",
        "web": "written text (blogs, news, comments)",
        "news": "written text (news, media)",
        "wiki": "Wikipedia",
        "uas": "Unlabelled dependencies",
        "las": "Labelled dependencies",
        "tags_acc": "Part-of-speech tags",
        "ents_f": "Entities (F-score)",
        "ents_p": "Entities (precision)",
        "ents_r": "Entities (recall)",
        "cpu": "words per second on CPU",
        "gpu": "words per second on GPU",
        "pipeline": "Processing pipeline components in order",
        "sources": "Sources of training data",
        "vecs": "Word vectors included in the model. Models that only support context vectors compute similarity via the tensors shared with the pipeline.",
        "benchmark_parser": "Parser accuracy",
        "benchmark_ner": "NER accuracy",
        "benchmark_speed": "Speed"
    },

    "MODEL_LICENSES": {
        "CC BY-SA":     "https://creativecommons.org/licenses/by-sa/3.0/",
        "CC BY-SA 3.0": "https://creativecommons.org/licenses/by-sa/3.0/",
        "CC BY-SA 4.0": "https://creativecommons.org/licenses/by-sa/4.0/",
        "CC BY-NC":     "https://creativecommons.org/licenses/by-nc/3.0/",
        "CC BY-NC 3.0": "https://creativecommons.org/licenses/by-nc/3.0/",
        "GPL":          "https://www.gnu.org/licenses/gpl.html",
        "LGPL":         "https://www.gnu.org/licenses/lgpl.html"
    },

    "MODEL_BENCHMARKS": {
        "parser": { "uas": "UAS", "las": "LAS", "tags_acc": "POS" },
        "ner":    { "ents_f": "NER F", "ents_p": "NER P", "ents_r": "NER R" },
        "speed":  { "nwords": "Words", "cpu": "w/s CPU", "gpu": "w/s GPU" }
    },

    "LANGUAGES": {
        "en": "English",
        "de": "German",
        "fr": "French",
        "es": "Spanish",
        "it": "Italian",
        "pt": "Portuguese",
        "nl": "Dutch",
        "sv": "Swedish",
        "fi": "Finnish",
        "nb": "Norwegian Bokmål",
        "da": "Danish",
        "hu": "Hungarian",
        "pl": "Polish",
        "ro": "Romanian",
        "hr": "Croatian",
        "tr": "Turkish",
        "he": "Hebrew",
        "ga": "Irish",
        "bn": "Bengali",
        "hi": "Hindi",
        "id": "Indonesian",
        "th": "Thai",
        "zh": "Chinese",
        "ja": "Japanese",
        "xx": "Multi-language"
    },

    "EXAMPLE_SENTENCES": {
        "en": "This is a sentence.",
        "de": "Dies ist ein Satz.",
        "fr": "C'est une phrase.",
        "es": "Esto es una frase.",
        "pt": "Esta é uma frase.",
        "it": "Questa è una frase.",
        "xx": "This is a sentence about Facebook."
    }
}