wav2vec2-cpt-base-ft-btb-cy / tokenizer_config.json
DewiBrynJones's picture
Training in progress, step 400
e8a586e verified
{
"added_tokens_decoder": {
"37": {
"content": "[UNK]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"38": {
"content": "[PAD]",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"39": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"40": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"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": "|"
}