{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "$", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "Replace", "pattern": { "Regex": "[^$;:,.!? abdefhijklmnopstuvwzɑɒɐæɔðəɚɛɜɡɪŋθɹɾʃʊʌʒʔˈˌː̩ᵻ]" }, "content": "" }, "pre_tokenizer": { "type": "Split", "pattern": { "Regex": "" }, "behavior": "Isolated", "invert": false }, "post_processor": { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "$", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "$", "type_id": 0 } } ], "special_tokens": { "$": { "id": "$", "ids": [ 0 ], "tokens": [ "$" ] } } }, "decoder": null, "model": { "vocab": { "$": 0, ";": 1, ":": 2, ",": 3, ".": 4, "!": 5, "?": 6, " ": 16, "a": 43, "b": 44, "d": 46, "e": 47, "f": 48, "h": 50, "i": 51, "j": 52, "k": 53, "l": 54, "m": 55, "n": 56, "o": 57, "p": 58, "s": 61, "t": 62, "u": 63, "v": 64, "w": 65, "z": 68, "ɑ": 69, "ɐ": 70, "æ": 72, "ɔ": 76, "ð": 81, "ə": 83, "ɚ": 85, "ɛ": 86, "ɜ": 87, "ɡ": 92, "ɪ": 102, "ŋ": 112, "θ": 119, "ɹ": 123, "ɾ": 125, "ʃ": 131, "ʊ": 135, "ʌ": 138, "ʒ": 147, "ʔ": 148, "ˈ": 156, "ˌ": 157, "ː": 158, "̩": 7, "ᵻ": 177, "ɒ": 71, "A": 24, "I": 25, "W": 39, "O": 31, "Y": 41, "Q": 33, "T": 36, "ʧ": 133, "ʤ": 82, "ᵊ": 42 } } }