Hugging Face's logo

AymanMansour
/
wav2vec2-arabic-l40s-eadi-phoneme

TensorBoard
Safetensors
wav2vec2
Model card Files Metrics Community
wav2vec2-arabic-l40s-eadi-phoneme / tokenizer_config.json
AymanMansour's picture
AymanMansour
Training in progress, step 1000
9e7765d verified
raw
history blame contribute delete
7.69 kB
 {
"added_tokens_decoder": {
"1": {
"content": "$$",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"3": {
"content": "**",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"6": {
"content": "AA",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"8": {
"content": "DD",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"10": {
"content": "EE",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"12": {
"content": "HH",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"13": {
"content": "I0",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"14": {
"content": "I1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"15": {
"content": "II0",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"17": {
"content": "SS",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"19": {
"content": "TT",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"20": {
"content": "U0",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"21": {
"content": "U1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"22": {
"content": "UU0",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"24": {
"content": "ZZ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"26": {
"content": "^^",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"28": {
"content": "aa",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"30": {
"content": "bb",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"32": {
"content": "dd",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"34": {
"content": "ff",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"37": {
"content": "hh",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"38": {
"content": "i0",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"39": {
"content": "i1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"40": {
"content": "ii0",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"42": {
"content": "jj",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"44": {
"content": "kk",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"46": {
"content": "ll",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"48": {
"content": "mm",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"50": {
"content": "nn",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"52": {
"content": "qq",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"54": {
"content": "rr",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"56": {
"content": "ss",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"58": {
"content": "tt",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"59": {
"content": "u0",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"60": {
"content": "u1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"61": {
"content": "uu0",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"63": {
"content": "ww",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"65": {
"content": "xx",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"67": {
"content": "yy",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"69": {
"content": "zz",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"70": {
"content": "[PAD]",
"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": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"73": {
"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>",
"extra_special_tokens": {},
"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": "|"
}