{ | |
"added_tokens_decoder": { | |
"0": { | |
"content": "<pad>", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"1": { | |
"content": "<s>", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"2": { | |
"content": "</s>", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"3": { | |
"content": "<unk>", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"5": { | |
"content": "num", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"6": { | |
"content": "ka", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"7": { | |
"content": "ta", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"8": { | |
"content": "thom", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"9": { | |
"content": "dhin", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"10": { | |
"content": "ki", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"11": { | |
"content": "tha", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"12": { | |
"content": "tham", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"13": { | |
"content": "dhi", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"14": { | |
"content": "cha", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"15": { | |
"content": "lam", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
}, | |
"16": { | |
"content": "thi", | |
"lstrip": true, | |
"normalized": false, | |
"rstrip": true, | |
"single_word": false, | |
"special": false | |
} | |
}, | |
"bos_token": "<s>", | |
"clean_up_tokenization_spaces": true, | |
"do_lower_case": false, | |
"eos_token": "</s>", | |
"model_max_length": 1000000000000000019884624838656, | |
"pad_token": "<pad>", | |
"processor_class": "Wav2Vec2Processor", | |
"replace_word_delimiter_char": " ", | |
"target_lang": null, | |
"tokenizer_class": "Wav2Vec2CTCTokenizer", | |
"unk_token": "<unk>", | |
"word_delimiter_token": "|" | |
} | |