| { |
| "added_tokens_decoder": { |
| "0": { |
| "content": "t'", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "2": { |
| "content": "s'", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "3": { |
| "content": "jy", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "4": { |
| "content": "n'", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "13": { |
| "content": "sj", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "18": { |
| "content": "ḗ", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "21": { |
| "content": "ā́", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "23": { |
| "content": "ndz", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "25": { |
| "content": "ī̌", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "26": { |
| "content": "ä́", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "29": { |
| "content": "zh", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "31": { |
| "content": "ū́", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "33": { |
| "content": "chj", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "34": { |
| "content": "dy", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "35": { |
| "content": "tsj", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "38": { |
| "content": "ū̀", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "41": { |
| "content": "ō̌", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "42": { |
| "content": "ndzh", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "44": { |
| "content": "jn", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "45": { |
| "content": "ä̌", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "47": { |
| "content": "ǚ", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "48": { |
| "content": "ë̌", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "49": { |
| "content": "tj", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "52": { |
| "content": "ë̂", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "54": { |
| "content": "ḯ", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "55": { |
| "content": "ä̀", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "56": { |
| "content": "ö̂", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "57": { |
| "content": "ē", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "58": { |
| "content": "ā̂", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "61": { |
| "content": "pj", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "62": { |
| "content": "ö̌", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "64": { |
| "content": "ǜ", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "65": { |
| "content": "ī̂", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "66": { |
| "content": "ō̂", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "67": { |
| "content": "ö̀", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "69": { |
| "content": "jw", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "70": { |
| "content": "ī", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "73": { |
| "content": "ū̌", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "77": { |
| "content": "ā̌", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "81": { |
| "content": "ī̀", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "82": { |
| "content": "kj", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "83": { |
| "content": "ë́", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "86": { |
| "content": "j'", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "87": { |
| "content": "ï̌", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "89": { |
| "content": "ö́", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "92": { |
| "content": "ō", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "93": { |
| "content": "ū̂", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "95": { |
| "content": "jñ", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "96": { |
| "content": "ä̂", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "98": { |
| "content": "ë̀", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "99": { |
| "content": "ü̂", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "102": { |
| "content": "ā̀", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "115": { |
| "content": "ū", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "116": { |
| "content": "ṓ", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "117": { |
| "content": "ǘ", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "123": { |
| "content": "ï̂", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "126": { |
| "content": "ṑ", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "127": { |
| "content": "jm", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "129": { |
| "content": "m'", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "130": { |
| "content": "ts'", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "133": { |
| "content": "'w", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "134": { |
| "content": "ñ'", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "135": { |
| "content": "k'", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "136": { |
| "content": "ch'", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "141": { |
| "content": "ā", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "145": { |
| "content": "ch", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "153": { |
| "content": "ï̀", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "156": { |
| "content": "ī́", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "160": { |
| "content": "...", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "161": { |
| "content": "[UNK]", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "162": { |
| "content": "[PAD]", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "163": { |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "164": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "bos_token": "<s>", |
| "clean_up_tokenization_spaces": false, |
| "do_lower_case": false, |
| "eos_token": "</s>", |
| "extra_special_tokens": {}, |
| "model_max_length": 1000000000000000019884624838656, |
| "pad_token": "[PAD]", |
| "replace_word_delimiter_char": " ", |
| "target_lang": "mmc", |
| "tokenizer_class": "Wav2Vec2CTCTokenizer", |
| "unk_token": "[UNK]", |
| "word_delimiter_token": "|" |
| } |
|
|
