False / tokenizer_config.json
1nnocent's picture
Upload tokenizer
1797bae verified
{
"add_blank": true,
"added_tokens_decoder": {
"0": {
"content": "r",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"51": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"52": {
"content": "\n",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"53": {
"content": "!",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"54": {
"content": "\"",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"55": {
"content": "%",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"56": {
"content": "(",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"57": {
"content": ")",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"58": {
"content": "*",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"59": {
"content": ",",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"60": {
"content": ".",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"61": {
"content": "/",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"62": {
"content": "0",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"63": {
"content": "1",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"64": {
"content": "2",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65": {
"content": "3",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"66": {
"content": "4",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"67": {
"content": "5",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"68": {
"content": "6",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"69": {
"content": "7",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"70": {
"content": "8",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"71": {
"content": "9",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"72": {
"content": ":",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"73": {
"content": "=",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"74": {
"content": "?",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"75": {
"content": "[",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"76": {
"content": "]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"77": {
"content": "`",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"78": {
"content": "c",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"79": {
"content": "j",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"80": {
"content": "q",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"81": {
"content": "~",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"82": {
"content": "¢",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"83": {
"content": "ð",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"84": {
"content": "ô",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"85": {
"content": "ā",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"86": {
"content": "ē",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"87": {
"content": "ȳ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"88": {
"content": "̄",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"89": {
"content": "ᴐ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"90": {
"content": "ṽ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"91": {
"content": "ỹ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"92": {
"content": "–",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"93": {
"content": "‘",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"94": {
"content": "’",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"95": {
"content": "“",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"96": {
"content": "”",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"97": {
"content": "₵",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"backend": "custom",
"clean_up_tokenization_spaces": true,
"is_local": true,
"is_uroman": false,
"language": "ewe",
"model_max_length": 1000000000000000019884624838656,
"normalize": true,
"pad_token": "r",
"phonemize": false,
"tokenizer_class": "VitsTokenizer",
"unk_token": "<unk>",
"verbose": false
}