Safetensors
wav2vec2-bert
wav2vec2bert-jyutping / tokenizer_config.json
indiejoseph's picture
Upload folder using huggingface_hub
1f89a01 verified
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"1": {
"content": "[UNK]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"2": {
"content": "|",
"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
},
"4": {
"content": "aai",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"5": {
"content": "aak",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"6": {
"content": "aam",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"7": {
"content": "aan",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"8": {
"content": "aang",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"9": {
"content": "aap",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"10": {
"content": "aat",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"11": {
"content": "aau",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"12": {
"content": "ai",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"13": {
"content": "ak",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"14": {
"content": "am",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"15": {
"content": "an",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"16": {
"content": "ang",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"17": {
"content": "ap",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"18": {
"content": "at",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"19": {
"content": "au",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"20": {
"content": "b",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"21": {
"content": "c",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"22": {
"content": "d",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"23": {
"content": "e",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"24": {
"content": "ei",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"25": {
"content": "ek",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"26": {
"content": "eng",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"27": {
"content": "eoi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"28": {
"content": "eon",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"29": {
"content": "eot",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"30": {
"content": "ep",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"31": {
"content": "eu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"32": {
"content": "f",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"33": {
"content": "g",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"34": {
"content": "gw",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"35": {
"content": "h",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"36": {
"content": "i",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"37": {
"content": "ik",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"38": {
"content": "im",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"39": {
"content": "in",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"40": {
"content": "ing",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"41": {
"content": "ip",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"42": {
"content": "it",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"43": {
"content": "iu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"44": {
"content": "j",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"45": {
"content": "k",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"46": {
"content": "kw",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"47": {
"content": "l",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"48": {
"content": "m",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"49": {
"content": "n",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"50": {
"content": "ng",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"51": {
"content": "o",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"52": {
"content": "oe",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"53": {
"content": "oek",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"54": {
"content": "oeng",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"55": {
"content": "oi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"56": {
"content": "ok",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"57": {
"content": "on",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"58": {
"content": "ong",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"59": {
"content": "ot",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"60": {
"content": "ou",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"61": {
"content": "p",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"62": {
"content": "s",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"63": {
"content": "t",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"64": {
"content": "u",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"65": {
"content": "ui",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"66": {
"content": "uk",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"67": {
"content": "un",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"68": {
"content": "ung",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"69": {
"content": "ut",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"70": {
"content": "w",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"71": {
"content": "yu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"72": {
"content": "yun",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"73": {
"content": "yut",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"74": {
"content": "z",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"75": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"76": {
"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>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"processor_class": "Wav2Vec2BertProcessor",
"replace_word_delimiter_char": " ",
"target_lang": null,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "[UNK]",
"word_delimiter_token": "|"
}