{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "special": true, "content": "[STOP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false }, { "id": 1, "special": true, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false }, { "id": 2, "special": true, "content": "[SPACE]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false } ], "normalizer": null, "pre_tokenizer": null, "post_processor": null, "decoder": null, "model": { "type": "BPE", "dropout": null, "unk_token": "[UNK]", "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "vocab": { "[STOP]": 0, "[UNK]": 1, "[SPACE]": 2, "!": 3, "'": 4, "(": 5, ")": 6, ",": 7, "-": 8, ".": 9, "/": 10, ":": 11, ";": 12, "?": 13, "a": 14, "aɪ": 15, "aʊ": 16, "b": 17, "d": 18, "d͡": 19, "d͡ʒ": 20, "e": 21, "eɪ": 22, "f": 23, "h": 24, "i": 25, "j": 26, "k": 27, "l": 28, "m": 29, "n": 30, "o": 31, "oʊ": 32, "p": 33, "s": 34, "t": 35, "t͡": 36, "t͡ʃ": 37, "u": 38, "v": 39, "w": 40, "z": 41, "|": 42, "æ": 43, "ð": 44, "ŋ": 45, "ɑ": 46, "ɔ": 47, "ɔɪ": 48, "ə": 49, "ɚ": 50, "ɛ": 51, "ɡ": 52, "ɪ": 53, "ɹ": 54, "ʃ": 55, "ʊ": 56, "ʌ": 57, "ʒ": 58, "θ": 59, "ː": 60 }, "merges": [ "a ɪ", "a ʊ", "d͡ ʒ", "e ɪ", "o ʊ", "t͡ ʃ", "ɔ ɪ" ] } }