urdu_processor_t5 / tokenizer_config.json
aarishshahmohsin's picture
Upload processor
2d272aa verified
raw
history blame
8.64 kB
{
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"79": {
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"80": {
"content": "<ctc_blank>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"81": {
"content": "ا",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"82": {
"content": "ب",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"83": {
"content": "پ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"84": {
"content": "ت",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"85": {
"content": "ٹ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"86": {
"content": "ث",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"87": {
"content": "ج",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"88": {
"content": "چ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"89": {
"content": "ح",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"90": {
"content": "خ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"91": {
"content": "د",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"92": {
"content": "ڈ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"93": {
"content": "ذ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"94": {
"content": "ر",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"95": {
"content": "ڑ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"96": {
"content": "ز",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"97": {
"content": "ژ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"98": {
"content": "س",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"99": {
"content": "ش",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"100": {
"content": "ص",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"101": {
"content": "ض",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"102": {
"content": "ط",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"103": {
"content": "ظ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"104": {
"content": "ع",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"105": {
"content": "غ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"106": {
"content": "ف",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"107": {
"content": "ق",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"108": {
"content": "ک",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"109": {
"content": "ل",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"110": {
"content": "م",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"111": {
"content": "ن",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"112": {
"content": "و",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"113": {
"content": "ہ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"114": {
"content": "ھ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"115": {
"content": "ی",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"116": {
"content": "ے",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"117": {
"content": "أ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"118": {
"content": "ؤ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"119": {
"content": "ئ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"120": {
"content": "گ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"121": {
"content": "ں",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"122": {
"content": "ۂ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"123": {
"content": "ۃ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"124": {
"content": "ۓ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"mask_token": "<mask>",
"model_max_length": 600,
"normalize": false,
"pad_token": "<pad>",
"processor_class": "SpeechT5Processor",
"sp_model_kwargs": {},
"tokenizer_class": "SpeechT5Tokenizer",
"unk_token": "<unk>"
}