wav2vec2_ljspeech_with_stress / tokenizer_config.json
jz703's picture
Upload processor
356395e
{
"added_tokens_decoder": {
"4": {
"content": "ˌʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"5": {
"content": "ˈʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"8": {
"content": "aɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"9": {
"content": "oʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"11": {
"content": "ˌu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"13": {
"content": "ˌaɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"14": {
"content": "ˌɑ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"17": {
"content": "ˈɑ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"19": {
"content": "ˈɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"20": {
"content": "ˌɛ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"21": {
"content": "ˈɔ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"22": {
"content": "ˈɛ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"24": {
"content": "ˌi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"26": {
"content": "ˈaʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"28": {
"content": "ɔɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"31": {
"content": "ˌɚ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"32": {
"content": "ˌoʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"33": {
"content": "ˈaɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"34": {
"content": "ˈi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"35": {
"content": "t͡ʃ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"36": {
"content": "ˈæ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"38": {
"content": "eɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"41": {
"content": "ˈʌ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"42": {
"content": "ˌæ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"45": {
"content": "ˌeɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"46": {
"content": "ˌʌ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"48": {
"content": "ˈeɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"50": {
"content": "ˈu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"52": {
"content": "ˌɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"53": {
"content": "ˌaʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"57": {
"content": "ˈɚ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"59": {
"content": "ˈɔɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"62": {
"content": "ˈoʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"63": {
"content": "aʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"65": {
"content": "ˌɔɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"66": {
"content": "ˌɔ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"69": {
"content": "d͡ʒ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"71": {
"content": "[UNK]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"72": {
"content": "[PAD]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"73": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"74": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"do_lower_case": false,
"eos_token": "</s>",
"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": "|"
}