dummy / tokenizer_config.json
adamchant's picture
Training in progress, step 1000
529f88a
{
"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": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"80": {
"content": "<ctc_blank>",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"81": {
"content": "ஃ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"82": {
"content": "அ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"83": {
"content": "ஆ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"84": {
"content": "இ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"85": {
"content": "ஈ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"86": {
"content": "உ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"87": {
"content": "ஊ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"88": {
"content": "எ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"89": {
"content": "ஏ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"90": {
"content": "ஐ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"91": {
"content": "ஒ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"92": {
"content": "ஓ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"93": {
"content": "ஔ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"94": {
"content": "க",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"95": {
"content": "ங",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"96": {
"content": "ச",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"97": {
"content": "ஜ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"98": {
"content": "ஞ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"99": {
"content": "ட",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"100": {
"content": "ண",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"101": {
"content": "த",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"102": {
"content": "ந",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"103": {
"content": "ன",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"104": {
"content": "ப",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"105": {
"content": "ம",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"106": {
"content": "ய",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"107": {
"content": "ர",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"108": {
"content": "ற",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"109": {
"content": "ல",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"110": {
"content": "ள",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"111": {
"content": "ழ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"112": {
"content": "வ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"113": {
"content": "ஶ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"114": {
"content": "ஷ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"115": {
"content": "ஸ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"116": {
"content": "ஹ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"117": {
"content": "ா",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"118": {
"content": "ி",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"119": {
"content": "ீ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"120": {
"content": "ு",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"121": {
"content": "ூ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"122": {
"content": "ெ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"123": {
"content": "ே",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"124": {
"content": "ை",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"125": {
"content": "ொ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"126": {
"content": "ோ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"127": {
"content": "ௌ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"128": {
"content": "்",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
},
"129": {
"content": "ௗ",
"lstrip": true,
"normalized": true,
"rstrip": true,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<s>",
"<pad>",
"</s>",
"<unk>",
"<mask>"
],
"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",
"tokenizer_file": null,
"unk_token": "<unk>"
}