xtts2-gpt / tokenizer_config.json
mlinmg's picture
Upload tokenizer_config.json
40ed473 verified
{
"added_tokens_decoder": {
"0": {
"content": "[STOP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[SPACE]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"259": {
"content": "[en]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"260": {
"content": "[de]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"261": {
"content": "[START]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"262": {
"content": "[fr]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"267": {
"content": "[ru]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"284": {
"content": "[es]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"285": {
"content": "[it]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"286": {
"content": "[pt]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"293": {
"content": "[cs]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"294": {
"content": "[pl]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"295": {
"content": "[tr]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"297": {
"content": "[nl]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5022": {
"content": "[ar]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5023": {
"content": "[zh-cn]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5412": {
"content": "[ja]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5753": {
"content": "[hu]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6152": {
"content": "[ko]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6680": {
"content": "[hi]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6681": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {"AutoTokenizer": ["AstraMindAI/xtts2-gpt--tokenizer.XTTSTokenizerFast", null]},
"bos_token": "[START]",
"clean_up_tokenization_spaces": true,
"eos_token": "[STOP]",
"max_length": null,
"model_max_length": 1000000000000000019884624838656,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "right",
"tokenizer_class": "XTTSTokenizerFast",
"unk_token": "[UNK]"
}