xls-asr-vi-40h-1B / tokenizer_config.json
geninhu's picture
Training in progress, step 1500
021380d
raw
history blame
187 Bytes
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2WordpieceTokenizer"}