{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 307, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 308, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "Sequence", "normalizers": [ { "type": "Replace", "pattern": { "String": "\\s+" }, "content": "|" } ] }, "pre_tokenizer": { "type": "Split", "pattern": { "String": "\\S" }, "behavior": "Isolated", "invert": false }, "post_processor": null, "decoder": { "type": "CTC", "pad_token": "[PAD]", "word_delimiter_token": "|", "cleanup": true }, "model": { "type": "WordLevel", "vocab": { "ʛ̥": 0, "k̚": 1, "z": 2, "ʋ": 3, "ʙ": 4, "æ̃": 5, "ɟ͡ʝ": 6, "p̚": 7, "kʘ": 8, "ɡ͡b": 9, "qǀ": 10, "ʌ̃": 11, "_": 12, "s": 13, "ʢ": 14, "ʡ͡ʜ": 15, "ẽ": 16, "χʼ": 17, "x": 18, "ʰ": 19, "̩": 20, "p": 21, "qǁ": 22, "ɶ̃": 23, "ɡǃ": 24, "ɺ̥": 25, "ʔ͡h": 26, "d͡z": 27, "ɞ": 28, "fʼ": 29, "ɳ": 30, "ŋ͡m": 31, "ʀ": 32, "ɵ̃": 33, "ð̠": 34, "ɒ̃": 35, "ⱱ": 36, "ʉ̃": 37, "ɺ": 38, "ᶮ": 39, "b̪͡v": 40, "ʲ": 41, "ɤ": 42, "t̪͡θʼ": 43, "ã": 44, "ɟ": 45, "ʏ̃": 46, "ɴʘ": 47, "ɲ": 48, "ɹ̠˔": 49, "ʟ̠": 50, "χ": 51, "ĩ": 52, "ʡ̆": 53, "qǃ": 54, "ỹ": 55, "ɮ": 56, "ɝ": 57, "ɥ̊": 58, "ɠ̊": 59, "ɾ": 60, "ɣ": 61, "õ": 62, "ɕʼ": 63, "kǃ": 64, "œ": 65, "ɯ̃": 66, "ʌ": 67, "qǂ": 68, "q": 69, "ɨ": 70, "ɢǃ": 71, "ø": 72, "b": 73, "θ": 74, "ʛ": 75, "ã": 76, "ʐ": 77, "t͡ʃʼ": 78, "ɡʘ": 79, "ä̃": 80, "n": 81, "ɤ̃": 82, "õ": 83, "b͡ꞵ": 84, "j": 85, "kʼ": 86, "kxʼ": 87, "n̼": 88, "ð": 89, "qʘ": 90, "n̥": 91, "ʃʼ": 92, "θ̼": 93, "t͡ɬ": 94, "ɻ˔": 95, "β": 96, "d͡ʒ": 97, "ʔ̞": 98, "E": 99, "qʼ": 100, "ɘ": 101, "ɭ̆": 102, "ɴǁ": 103, "̃": 104, "ɛ": 105, "ɖ": 106, "ʊ": 107, "ɢǀ": 108, "t̚": 109, "ɡ͡ɣ": 110, "ɥ": 111, "ɡǀ": 112, "ʕ": 113, "ɬ": 114, "ɽ": 115, "ɢǂ": 116, "ɒ": 117, "ɤ̞": 118, "ɐ̃": 119, "ɭ": 120, "ø̞": 121, "ᶿ": 122, "ʡ͡ʢ": 123, "ɶ": 124, "ʟ": 125, "ẽ̞": 126, "ɑ̃": 127, "ɴǃ": 128, "ɨ̃": 129, "ɴ": 130, "ᶰ": 131, "ɐ": 132, "b̪": 133, "ɹ̠̊˔": 134, "ʎ̝̊": 135, "ɳ̊": 136, "t͡ɬʼ": 137, "w": 138, "ɹ": 139, "t": 140, "a": 141, "ʒ": 142, "ɕ": 143, "ä": 144, "i": 145, "kǀ": 146, "ɰ": 147, "ɘ̃": 148, "ʑ": 149, "ɻ̊˔": 150, "ʔ": 151, "ɾ̥": 152, "ɚ": 153, "ʜ": 154, "ɯ": 155, "ʎ̆": 156, "O": 157, "ʡ": 158, "ᶑ": 159, "ɡ": 160, "ɞ̃": 161, "ɭ˔": 162, "ɬʼ": 163, "ⱱ̟": 164, "ᵑ": 165, "ø̃": 166, "ə": 167, "ɢǁ": 168, "ɲ̊": 169, "p̪͡f": 170, "ŋǀ": 171, "c": 172, "d͡ð": 173, "ʙ̥": 174, "{": 175, "r̥": 176, "e": 177, "t̼": 178, "ŋǁ": 179, "ʈ͡ʂ": 180, "ʎ": 181, "ʝ": 182, "ˠ": 183, "ũ": 184, "ɜ̃": 185, "ɾ̼": 186, "p͡f": 187, "r": 188, "k͡p": 189, "k͡x": 190, "d͡ɮ": 191, "θʼ": 192, "ʈ": 193, "ɴǀ": 194, "ᶑ̊": 195, "ɡǁ": 196, "˞": 197, "o̞": 198, "ɔ̃": 199, "ʄ": 200, "ɢʘ": 201, "ɡǂ": 202, "ẽ": 203, "ʟ̝̊": 204, "ɗ̥": 205, "y": 206, "ŋǂ": 207, "q͡χʼ": 208, "m": 209, "kǁ": 210, "ɓ̥": 211, "ɪ̃": 212, "tʼ": 213, "ɗ": 214, "ʃ": 215, "ʈ͡ʂʼ": 216, "ɱ": 217, "ɢ̆": 218, "ˡ": 219, "ʊ̃": 220, "ç": 221, "v": 222, "q͡ʡ": 223, "c͡ç": 224, "ʏ": 225, "ɠ": 226, "ŋǃ": 227, "ŋ": 228, "ə̃": 229, "kǂ": 230, "A": 231, "q͡ꭓ": 232, "ʡʼ": 233, "ⁿ": 234, "œ̃": 235, "ø̞̃": 236, "ʈʼ": 237, "ɛ̃": 238, "pʼ": 239, "ː": 240, "o": 241, "ð̼": 242, "f": 243, "ʟ̝": 244, "t͡s": 245, "ũ": 246, "ɢ͡ʁ": 247, "æ": 248, "θ̠": 249, "ʄ̊": 250, "ɢ": 251, "ɜ": 252, "ɓ": 253, "ʁ": 254, "ɴǂ": 255, "ɵ": 256, "ʂʼ": 257, "õ̞": 258, "ˣ": 259, "ꞎ": 260, "ɤ̞̃": 261, "ɸ": 262, "ɽ̊": 263, "t͡ɕ": 264, "m̥": 265, "ʍ": 266, "ᶬ": 267, "ɻ": 268, "d̼": 269, "ŋʘ": 270, "I": 271, "ɸʼ": 272, "}": 273, "t͡sʼ": 274, "ɔ": 275, "l": 276, "ʉ": 277, "ɑ": 278, "sʼ": 279, "ħ": 280, "t͡θ": 281, "e̞": 282, "ʀ̥": 283, "t͡ʃ": 284, "k": 285, "ɡ̆": 286, "ˤ": 287, "ɧ": 288, "ʎ̝": 289, "h": 290, "d͡ʑ": 291, "ʂ": 292, "p̪": 293, "ᵐ": 294, "xʼ": 295, "ɪ": 296, "u": 297, "ɖ͡ʐ": 298, "ʷ": 299, "ʟ̆": 300, "cʼ": 301, "ɭ̥̆": 302, "ᶯ": 303, "ŋ̊": 304, "p͡ɸ": 305, "d": 306, "[UNK]": 307, "[PAD]": 308 }, "unk_token": "[UNK]" } }