wav2vec2-xls-r-300m-phoneme_he1 / tokenizer_config.json
dima1234321's picture
Upload tokenizer
624d1cc verified
{
"added_tokens_decoder": {
"3": {
"content": "ba",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"4": {
"content": "be",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"5": {
"content": "bi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"6": {
"content": "bo",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"7": {
"content": "bu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"9": {
"content": "da",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"10": {
"content": "de",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"11": {
"content": "di",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"12": {
"content": "do",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"13": {
"content": "du",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"17": {
"content": "ga",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"18": {
"content": "ge",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"19": {
"content": "gi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"20": {
"content": "go",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"21": {
"content": "gu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"23": {
"content": "ha",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"24": {
"content": "he",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"25": {
"content": "hi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"26": {
"content": "ho",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"27": {
"content": "hu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"30": {
"content": "ka",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"31": {
"content": "ke",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"32": {
"content": "ki",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"33": {
"content": "ko",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"34": {
"content": "ku",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"36": {
"content": "la",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"37": {
"content": "le",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"38": {
"content": "li",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"39": {
"content": "lo",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"40": {
"content": "lu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"45": {
"content": "pa",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"46": {
"content": "pe",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"47": {
"content": "pi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"48": {
"content": "po",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"49": {
"content": "pu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"51": {
"content": "ra",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"52": {
"content": "re",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"53": {
"content": "ri",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"54": {
"content": "ro",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"55": {
"content": "ru",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"57": {
"content": "sa",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"58": {
"content": "se",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"59": {
"content": "sh",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"60": {
"content": "sha",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"61": {
"content": "she",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"62": {
"content": "shi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"63": {
"content": "sho",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"64": {
"content": "shu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"65": {
"content": "si",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"66": {
"content": "so",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"67": {
"content": "su",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"69": {
"content": "ta",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"70": {
"content": "te",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"71": {
"content": "ti",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"72": {
"content": "to",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"73": {
"content": "tu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"74": {
"content": "tz",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"77": {
"content": "va",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"78": {
"content": "ve",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"79": {
"content": "vi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"80": {
"content": "vo",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"81": {
"content": "vu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"83": {
"content": "xa",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"84": {
"content": "xe",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"85": {
"content": "xi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"86": {
"content": "xo",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"87": {
"content": "xu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"89": {
"content": "ya",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"90": {
"content": "ye",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"91": {
"content": "yi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"92": {
"content": "yo",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"93": {
"content": "yu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"95": {
"content": "za",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"96": {
"content": "ze",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"97": {
"content": "zi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"98": {
"content": "zo",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"99": {
"content": "zu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"100": {
"content": "[UNK]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"101": {
"content": "[PAD]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"102": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"do_lower_case": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"replace_word_delimiter_char": " ",
"target_lang": null,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "[UNK]",
"word_delimiter_token": "|"
}