mms-300m-1130-forced-aligner / tokenizer_config.json
MahmoudAshraf's picture
Fix Tokenizer Vocab for CTranslate2 Conversion
f247a97 verified
{
"added_tokens_decoder": {
"0": {
"content": "<blank>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
}
},
"bos_token": null,
"clean_up_tokenization_spaces": true,
"do_lower_case": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"replace_word_delimiter_char": " ",
"target_lang": null,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "<unk>",
"word_delimiter_token": "|"
}