test / tokenizer_config.json
vincentlui's picture
Training in progress, step 100
3815ce9
raw
history blame
454 Bytes
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"do_lower_case": false,
"do_normalize": true,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"processor_class": "Wav2Vec2Processor",
"replace_word_delimiter_char": " ",
"return_attention_mask": false,
"target_lang": null,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "<unk>",
"word_delimiter_token": "|"
}