Phone-aid / models /SA /tokenizer_config.json
Mostafa Shahin
First Commit
4c01711
raw
history blame
13 kB
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"1": {
"content": "p_alveolar",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"2": {
"content": "n_alveolar",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"3": {
"content": "p_palatal",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"4": {
"content": "n_palatal",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"5": {
"content": "p_dental",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"6": {
"content": "n_dental",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"7": {
"content": "p_glottal",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"8": {
"content": "n_glottal",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"9": {
"content": "p_labial",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"10": {
"content": "n_labial",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"11": {
"content": "p_velar",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"12": {
"content": "n_velar",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"13": {
"content": "p_anterior",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"14": {
"content": "n_anterior",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"15": {
"content": "p_posterior",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"16": {
"content": "n_posterior",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"17": {
"content": "p_retroflex",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"18": {
"content": "n_retroflex",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"19": {
"content": "p_mid",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"20": {
"content": "n_mid",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"21": {
"content": "p_high",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"22": {
"content": "n_high",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"23": {
"content": "p_low",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"24": {
"content": "n_low",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"25": {
"content": "p_front",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"26": {
"content": "n_front",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"27": {
"content": "p_back",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"28": {
"content": "n_back",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"29": {
"content": "p_central",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"30": {
"content": "n_central",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"31": {
"content": "p_consonant",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"32": {
"content": "n_consonant",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"33": {
"content": "p_sonorant",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"34": {
"content": "n_sonorant",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"35": {
"content": "p_long",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"36": {
"content": "n_long",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"37": {
"content": "p_short",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"38": {
"content": "n_short",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"39": {
"content": "p_vowel",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"40": {
"content": "n_vowel",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"41": {
"content": "p_semivowel",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"42": {
"content": "n_semivowel",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"43": {
"content": "p_fricative",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"44": {
"content": "n_fricative",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"45": {
"content": "p_nasal",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"46": {
"content": "n_nasal",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"47": {
"content": "p_stop",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"48": {
"content": "n_stop",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"49": {
"content": "p_approximant",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"50": {
"content": "n_approximant",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"51": {
"content": "p_affricate",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"52": {
"content": "n_affricate",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"53": {
"content": "p_liquid",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"54": {
"content": "n_liquid",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"55": {
"content": "p_continuant",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"56": {
"content": "n_continuant",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"57": {
"content": "p_monophthong",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"58": {
"content": "n_monophthong",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"59": {
"content": "p_diphthong",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"60": {
"content": "n_diphthong",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"61": {
"content": "p_round",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"62": {
"content": "n_round",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"63": {
"content": "p_voiced",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"64": {
"content": "n_voiced",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"65": {
"content": "p_bilabial",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"66": {
"content": "n_bilabial",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"67": {
"content": "p_coronal",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"68": {
"content": "n_coronal",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"69": {
"content": "p_dorsal",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"70": {
"content": "n_dorsal",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"71": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"72": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73": {
"content": "<unk>",
"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>",
"processor_class": "Wav2Vec2Processor",
"replace_word_delimiter_char": " ",
"target_lang": null,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "<unk>",
"word_delimiter_token": ""
}