{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": { "type": "Whitespace" }, "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, "byte_fallback": false, "vocab": { "[UNK]": 0, "[CLS]": 1, "[SEP]": 2, "[PAD]": 3, "[MASK]": 4, "!": 5, "#": 6, "*": 7, ",": 8, "-": 9, ".": 10, "=": 11, "?": 12, "N": 13, "Q": 14, "^": 15, "_": 16, "`": 17, "a": 18, "b": 19, "d": 20, "e": 21, "f": 22, "g": 23, "h": 24, "i": 25, "j": 26, "k": 27, "l": 28, "m": 29, "n": 30, "o": 31, "p": 32, "s": 33, "t": 34, "u": 35, "v": 36, "w": 37, "x": 38, "y": 39, "z": 40, "~": 41, "æ": 42, "ç": 43, "ð": 44, "ŋ": 45, "ɑ": 46, "ɔ": 47, "ə": 48, "ɛ": 49, "ɥ": 50, "ɪ": 51, "ɫ": 52, "ɯ": 53, "ɸ": 54, "ɹ": 55, "ɾ": 56, "ʃ": 57, "ʊ": 58, "ʑ": 59, "ʒ": 60, "ʰ": 61, "ˈ": 62, "ˌ": 63, "θ": 64, "…": 65, "⁼": 66, "↑": 67, "→": 68, "↓": 69 }, "merges": [ ] } }