{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": { "type": "WhitespaceSplit" }, "post_processor": { "type": "TemplateProcessing", "single": [ { "Sequence": { "id": "A", "type_id": 0 } } ], "pair": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } } ], "special_tokens": {} }, "decoder": null, "model": { "type": "WordLevel", "vocab": { "": 0, "A": 1, "E": 2, "I": 3, "N": 4, "O": 5, "U": 6, "a": 7, "b": 8, "by": 9, "ch": 10, "cl": 11, "d": 12, "dy": 13, "e": 14, "f": 15, "g": 16, "gy": 17, "h": 18, "hy": 19, "i": 20, "j": 21, "k": 22, "ky": 23, "m": 24, "my": 25, "n": 26, "ny": 27, "o": 28, "p": 29, "py": 30, "r": 31, "ry": 32, "s": 33, "sh": 34, "t": 35, "ts": 36, "ty": 37, "u": 38, "v": 39, "w": 40, "y": 41, "z": 42, "pau": 43 }, "unk_token": "" } }