sayest-duration / tokenizer_config.json
alzavo's picture
Upload folder using huggingface_hub
93c5d28 verified
{
"added_tokens_decoder": {
"1": {
"content": "a:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"2": {
"content": "aa",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"3": {
"content": "aa:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"5": {
"content": "e:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"6": {
"content": "ee",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"7": {
"content": "ee:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"9": {
"content": "ff",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"11": {
"content": "h:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"13": {
"content": "i:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"14": {
"content": "ii",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"15": {
"content": "ii:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"18": {
"content": "k:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"19": {
"content": "k:k",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"20": {
"content": "kk",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"22": {
"content": "l'",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"23": {
"content": "l':l",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"24": {
"content": "l'l",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"25": {
"content": "l:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"26": {
"content": "l:l",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"27": {
"content": "ll",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"29": {
"content": "m:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"30": {
"content": "mm",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"32": {
"content": "n'",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"33": {
"content": "n':",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"34": {
"content": "n':n",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"35": {
"content": "n:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"36": {
"content": "n:n",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"37": {
"content": "nn",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"39": {
"content": "o:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"40": {
"content": "oo",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"41": {
"content": "oo:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"43": {
"content": "p:p",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"44": {
"content": "pp",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"46": {
"content": "r:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"47": {
"content": "rr",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"49": {
"content": "s'",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"50": {
"content": "s':s",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"51": {
"content": "s:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"52": {
"content": "s:s",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"53": {
"content": "ss",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"55": {
"content": "t'",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"56": {
"content": "t':",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"57": {
"content": "t':t",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"58": {
"content": "t't",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"59": {
"content": "t:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"60": {
"content": "t:t",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"61": {
"content": "tt",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"63": {
"content": "uu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"64": {
"content": "uu:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"66": {
"content": "v:v",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"67": {
"content": "vv",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"70": {
"content": "ää",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"72": {
"content": "õõ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"74": {
"content": "öö",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"75": {
"content": "öö:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"77": {
"content": "üü",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"78": {
"content": "[UNK]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"79": {
"content": "[PAD]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"80": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"81": {
"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]",
"processor_class": "Wav2Vec2Processor",
"replace_word_delimiter_char": " ",
"target_lang": null,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "[UNK]",
"word_delimiter_token": "None"
}