DeepSahel-Kikuyu-ASR-Optimized / tokenizer_config.json
InterstellarCG's picture
Publish DeepSahel MMS CTC Kikuyu Muon Ext3
d3fc119 verified
Raw
History Blame Contribute Delete
2.2 kB
{
"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
},
"39": {
"content": "3",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"40": {
"content": "5",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"41": {
"content": "6",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"42": {
"content": "7",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"43": {
"content": "8",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"44": {
"content": "9",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"backend": "custom",
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"do_lower_case": false,
"eos_token": "</s>",
"is_local": false,
"model_max_length": 1000000000000000019884624838656,
"model_specific_special_tokens": {
"word_delimiter_token": "|"
},
"pad_token": "<pad>",
"processor_class": "Wav2Vec2Processor",
"replace_word_delimiter_char": " ",
"target_lang": "kik",
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "<unk>",
"word_delimiter_token": "|"
}