| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "aa", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "1": { | |
| "content": "ae", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "2": { | |
| "content": "ah", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "3": { | |
| "content": "ao", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "4": { | |
| "content": "aw", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "5": { | |
| "content": "ax", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "6": { | |
| "content": "ax-h", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "7": { | |
| "content": "axr", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "8": { | |
| "content": "ay", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "10": { | |
| "content": "bcl", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "11": { | |
| "content": "ch", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "13": { | |
| "content": "dcl", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "14": { | |
| "content": "dh", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "15": { | |
| "content": "dx", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "16": { | |
| "content": "eh", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "17": { | |
| "content": "el", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "18": { | |
| "content": "em", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "19": { | |
| "content": "en", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "20": { | |
| "content": "eng", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "21": { | |
| "content": "epi", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "22": { | |
| "content": "er", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "23": { | |
| "content": "ey", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "26": { | |
| "content": "gcl", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "27": { | |
| "content": "hh", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "28": { | |
| "content": "hv", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "29": { | |
| "content": "ih", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "30": { | |
| "content": "ix", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "31": { | |
| "content": "iy", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "32": { | |
| "content": "jh", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "34": { | |
| "content": "kcl", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "38": { | |
| "content": "ng", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "39": { | |
| "content": "nx", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "40": { | |
| "content": "ow", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "41": { | |
| "content": "oy", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "43": { | |
| "content": "pau", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "44": { | |
| "content": "pcl", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "48": { | |
| "content": "sh", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50": { | |
| "content": "tcl", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "51": { | |
| "content": "th", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "52": { | |
| "content": "uh", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "53": { | |
| "content": "uw", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "54": { | |
| "content": "ux", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "59": { | |
| "content": "zh", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "60": { | |
| "content": "[UNK]", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "61": { | |
| "content": "[PAD]", | |
| "lstrip": true, | |
| "normalized": false, | |
| "rstrip": true, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "62": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "63": { | |
| "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": null, | |
| "tokenizer_class": "Wav2Vec2CTCTokenizer", | |
| "unk_token": "[UNK]", | |
| "word_delimiter_token": "|" | |
| } | |