|
{ |
|
"added_tokens_decoder": { |
|
"3": { |
|
"content": "ˌɛ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"4": { |
|
"content": "oʊ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"5": { |
|
"content": "uː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"6": { |
|
"content": "oː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"8": { |
|
"content": "ˌɐ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"9": { |
|
"content": "ɪɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"10": { |
|
"content": "ˈaɪ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"11": { |
|
"content": "ˈɑː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"13": { |
|
"content": "ˌiə", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"15": { |
|
"content": "ˈaʊ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"18": { |
|
"content": "ˌʊɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"19": { |
|
"content": "aʊ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"21": { |
|
"content": "ˌaʊ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"22": { |
|
"content": "ˈoʊ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"24": { |
|
"content": "ˌʌ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"25": { |
|
"content": "ˈæ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"26": { |
|
"content": "əl", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"27": { |
|
"content": "ɔːɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"28": { |
|
"content": "ˌɑː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"29": { |
|
"content": "ˌoː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"30": { |
|
"content": "ˈɜː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"32": { |
|
"content": "ˈaɪə", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"33": { |
|
"content": "ˈaɪɚ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"34": { |
|
"content": "aɪɚ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"35": { |
|
"content": "ˈoː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"37": { |
|
"content": "ˌɛɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"40": { |
|
"content": "dʒ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"41": { |
|
"content": "ˌɜː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"42": { |
|
"content": "ˈiː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"43": { |
|
"content": "ɑː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"44": { |
|
"content": "ˈʊ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"46": { |
|
"content": "ˌaɪ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"49": { |
|
"content": "aɪ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"50": { |
|
"content": "n̩", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"51": { |
|
"content": "tʃ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"52": { |
|
"content": "ˌæ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"53": { |
|
"content": "ˈɔɪ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"54": { |
|
"content": "ˈɪ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"55": { |
|
"content": "ˈeɪ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"56": { |
|
"content": "ˌʊ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"57": { |
|
"content": "ˈɔ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"60": { |
|
"content": "ɛɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"62": { |
|
"content": "ˈiə", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"63": { |
|
"content": "ˌuː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"64": { |
|
"content": "ˌɔː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"65": { |
|
"content": "oːɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"66": { |
|
"content": "ˌɔɪ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"70": { |
|
"content": "iə", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"71": { |
|
"content": "eɪ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"72": { |
|
"content": "ˌɪɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"74": { |
|
"content": "ˌeɪ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"75": { |
|
"content": "ˈʌ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"76": { |
|
"content": "ɑːɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"79": { |
|
"content": "ˈɛ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"80": { |
|
"content": "ˌɑːɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"81": { |
|
"content": "ˌaɪɚ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"83": { |
|
"content": "ˈɪɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"84": { |
|
"content": "ˈuː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"86": { |
|
"content": "aɪə", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"87": { |
|
"content": "ˌɔ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"88": { |
|
"content": "ˈɔːɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"91": { |
|
"content": "ɔː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"92": { |
|
"content": "ʊɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"94": { |
|
"content": "ˈɛɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"95": { |
|
"content": "ˈɑːɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"96": { |
|
"content": "ˌoʊ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"97": { |
|
"content": "ˌoːɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"98": { |
|
"content": "ˈoːɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100": { |
|
"content": "ˈɔː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"101": { |
|
"content": "ɔɪ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"103": { |
|
"content": "ɜː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"104": { |
|
"content": "iː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"106": { |
|
"content": "ˌn̩", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"107": { |
|
"content": "ˌɔːɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"109": { |
|
"content": "ˌiː", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"110": { |
|
"content": "ˈɚ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"112": { |
|
"content": "ˈʊɹ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"115": { |
|
"content": "ˌɪ", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"116": { |
|
"content": "[UNK]", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"117": { |
|
"content": "[PAD]", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"118": { |
|
"content": "<s>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"119": { |
|
"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": "|" |
|
} |
|
|