hubert-base-english-ipa / tokenizer_config.json
speech31's picture
upload model
068102d
raw
history blame
181 Bytes
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}