cdial-yoruba-test / tokenizer_config.json

add tokenizer

d394297 almost 3 years ago

181 Bytes

{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}