speecht5_large_slr43 / tokenizer_config.json
aryamanstha's picture
Training in progress, step 1000
001825a verified
raw
history blame
13.9 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": "अ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"82": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"83": {
"content": "आ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"84": {
"content": "इ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"85": {
"content": "ई",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"86": {
"content": "उ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"87": {
"content": "ऊ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"88": {
"content": "ऋ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"89": {
"content": "ए",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"90": {
"content": "ऐ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"91": {
"content": "ओ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"92": {
"content": "औ",
"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": "ः",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"95": {
"content": "ॠ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"96": {
"content": "क",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"97": {
"content": "ख",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"98": {
"content": "ग",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"99": {
"content": "घ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"100": {
"content": "ङ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"101": {
"content": "च",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"102": {
"content": "छ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"103": {
"content": "ज",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"104": {
"content": "झ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"105": {
"content": "ञ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"106": {
"content": "ट",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"107": {
"content": "ठ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"108": {
"content": "ड",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"109": {
"content": "ढ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"110": {
"content": "ण",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"111": {
"content": "त",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"112": {
"content": "थ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"113": {
"content": "द",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"114": {
"content": "ध",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"115": {
"content": "न",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"116": {
"content": "प",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"117": {
"content": "फ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"118": {
"content": "ब",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"119": {
"content": "भ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"120": {
"content": "म",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"121": {
"content": "य",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"122": {
"content": "र",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"123": {
"content": "ल",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"124": {
"content": "व",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"125": {
"content": "श",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"126": {
"content": "ष",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"127": {
"content": "स",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"128": {
"content": "ह",
"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": "ा",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"131": {
"content": "ि",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"132": {
"content": "ी",
"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": "ू",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"135": {
"content": "ृ",
"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": "ॅ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"138": {
"content": "ॆ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"139": {
"content": "े",
"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
},
"142": {
"content": "ॊ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"143": {
"content": "ो",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"144": {
"content": "ौ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"145": {
"content": "ँ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"146": {
"content": "०",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"147": {
"content": "१",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"148": {
"content": "२",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"149": {
"content": "३",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"150": {
"content": "४",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151": {
"content": "५",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"152": {
"content": "६",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"153": {
"content": "७",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"154": {
"content": "८",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"155": {
"content": "९",
"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>"
}