wav2vec2-large-xlsr-53-estonian / tokenizer_config.json
speech-test's picture
First model
268604c
raw
history blame contribute delete
138 Bytes
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|"}