tokenizer.json

{
    "version": "1.0",
    "truncation": null,
    "padding": null,
    "added_tokens": [
        {
            "id": 30,
            "content": "<unk>",
            "single_word": false,
            "lstrip": false,
            "rstrip": false,
            "normalized": false,
            "special": true
        }
    ],
    "normalizer": {
        "type": "Sequence",
        "normalizers": [
            {
                "type": "Lowercase"
            },
            {
                "type": "Replace",
                "pattern": {
                    "Regex": "[^ '\\-_abcdefghijklmnopqrstuvwxyz]"
                },
                "content": ""
            },
            {
                "type": "Strip",
                "strip_left": true,
                "strip_right": true
            },
            {
                "type": "Replace",
                "pattern": {
                    "Regex": "(?=.)|(?<!^)$"
                },
                "content": "h"
            }
        ]
    },
    "pre_tokenizer": {
        "type": "Split",
        "pattern": {
            "Regex": ""
        },
        "behavior": "Isolated",
        "invert": false
    },
    "post_processor": null,
    "decoder": null,
    "model": {
        "type": "WordLevel",
        "vocab": {
            " ": 26,
            "'": 4,
            "-": 18,
            "_": 25,
            "a": 20,
            "b": 22,
            "c": 24,
            "d": 15,
            "e": 27,
            "f": 19,
            "g": 13,
            "h": 0,
            "i": 16,
            "j": 12,
            "k": 11,
            "l": 5,
            "m": 7,
            "n": 14,
            "o": 8,
            "p": 9,
            "q": 29,
            "r": 6,
            "s": 3,
            "t": 17,
            "u": 28,
            "v": 10,
            "w": 2,
            "x": 21,
            "y": 23,
            "z": 1,
            "<unk>": 30
        },
        "unk_token": "<unk>"
    }
}