| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "+ุง", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "+ู", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "ุจ+", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "+ูู ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "4": { | |
| "content": "+ุงุช", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "5": { | |
| "content": "+ู", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "6": { | |
| "content": "ู+", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "7": { | |
| "content": "+ูู ุง", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "8": { | |
| "content": "+ูุง", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "9": { | |
| "content": "+ู", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "10": { | |
| "content": "+ูุง", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "11": { | |
| "content": "+ูู ุง", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "12": { | |
| "content": "+ุฉ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "13": { | |
| "content": "ู+", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "14": { | |
| "content": "+ูู ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "15": { | |
| "content": "+ูู", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "16": { | |
| "content": "+ุช", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "17": { | |
| "content": "[ุจุฑูุฏ]", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "18": { | |
| "content": "[ู ุณุชุฎุฏู ]", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "19": { | |
| "content": "ูู+", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "20": { | |
| "content": "ุงู+", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "21": { | |
| "content": "[ุฑุงุจุท]", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "22": { | |
| "content": "ุณ+", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "23": { | |
| "content": "+ุงู", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "24": { | |
| "content": "+ูุง", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "25": { | |
| "content": "+ู", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "26": { | |
| "content": "+ูู", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "27": { | |
| "content": "+ูู", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "28": { | |
| "content": "+ูู", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "29": { | |
| "content": "ู+", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "30": { | |
| "content": "ู+", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": true, | |
| "special": true | |
| }, | |
| "31": { | |
| "content": "[PAD]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "32": { | |
| "content": "[UNK]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "33": { | |
| "content": "[CLS]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "34": { | |
| "content": "[SEP]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "35": { | |
| "content": "[MASK]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "[CLS]", | |
| "do_basic_tokenize": true, | |
| "do_lower_case": false, | |
| "extra_special_tokens": {}, | |
| "mask_token": "[MASK]", | |
| "max_len": 512, | |
| "model_max_length": 512, | |
| "never_split": [ | |
| "+ู", | |
| "+ูู ุง", | |
| "ู+", | |
| "+ูุง", | |
| "+ูู", | |
| "ู+", | |
| "+ูู", | |
| "+ุงู", | |
| "+ูู ", | |
| "+ุฉ", | |
| "[ุจุฑูุฏ]", | |
| "ูู+", | |
| "+ู", | |
| "+ุช", | |
| "+ู", | |
| "ุณ+", | |
| "ู+", | |
| "[ู ุณุชุฎุฏู ]", | |
| "+ูู ", | |
| "+ุง", | |
| "ุจ+", | |
| "ู+", | |
| "+ูุง", | |
| "+ูุง", | |
| "+ูู", | |
| "+ูู ุง", | |
| "ุงู+", | |
| "+ู", | |
| "+ูู", | |
| "+ุงุช", | |
| "[ุฑุงุจุท]" | |
| ], | |
| "pad_token": "[PAD]", | |
| "processor_class": "TrOCRProcessor", | |
| "sep_token": "[SEP]", | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "unk_token": "[UNK]" | |
| } | |