v2-wav2vec2-base-common-voice-fr / tokenizer_config.json
nawel-ucsb's picture
Upload tokenizer
fe8dc20
raw
history blame
236 Bytes
{
"bos_token": "<s>",
"do_lower_case": false,
"eos_token": "</s>",
"pad_token": "[PAD]",
"replace_word_delimiter_char": " ",
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "[UNK]",
"word_delimiter_token": "|"
}