{ | |
"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": "ق", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"82": { | |
"content": "ي", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"83": { | |
"content": "ۀ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"84": { | |
"content": "ف", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"85": { | |
"content": "ح", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"86": { | |
"content": "ی", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"87": { | |
"content": "،", | |
"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": "ٌ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"90": { | |
"content": "ز", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"91": { | |
"content": "ج", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"92": { | |
"content": "ث", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"93": { | |
"content": " ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"94": { | |
"content": "ء", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"95": { | |
"content": "“", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"96": { | |
"content": "ؤ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"97": { | |
"content": "س", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"98": { | |
"content": "ص", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"99": { | |
"content": "ژ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"100": { | |
"content": "ک", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"101": { | |
"content": "ً", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"102": { | |
"content": "ن", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"103": { | |
"content": "ُ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"104": { | |
"content": "ش", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"105": { | |
"content": "ب", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"106": { | |
"content": "؛", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"107": { | |
"content": "«", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"108": { | |
"content": "پ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"109": { | |
"content": "گ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"110": { | |
"content": "ى", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"111": { | |
"content": "ه", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"112": { | |
"content": "ے", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"113": { | |
"content": "ظ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"114": { | |
"content": "ت", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"115": { | |
"content": "ِ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"116": { | |
"content": "أ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"117": { | |
"content": "غ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"118": { | |
"content": "و", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"119": { | |
"content": "ة", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"120": { | |
"content": "ط", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"121": { | |
"content": "ع", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"122": { | |
"content": "ك", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"123": { | |
"content": "د", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"124": { | |
"content": "خ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"125": { | |
"content": "=", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"126": { | |
"content": "»", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"127": { | |
"content": "ل", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"128": { | |
"content": "؟", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"129": { | |
"content": "”", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"130": { | |
"content": "آ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"131": { | |
"content": "م", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"132": { | |
"content": "ئ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"133": { | |
"content": "َ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"134": { | |
"content": "ر", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"135": { | |
"content": "ا", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"136": { | |
"content": "–", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"137": { | |
"content": "ذ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"138": { | |
"content": "ض", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"139": { | |
"content": "ـ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"140": { | |
"content": "ّ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
}, | |
"141": { | |
"content": "ٔ", | |
"lstrip": false, | |
"normalized": true, | |
"rstrip": false, | |
"single_word": false, | |
"special": false | |
} | |
}, | |
"bos_token": "<s>", | |
"clean_up_tokenization_spaces": true, | |
"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>" | |
} | |