wav2vec2-ctc-gigaspeech / tokenizer_config.json
esc-bencher's picture
Add training scripts and weights
4f9ac96
raw
history blame
343 Bytes
{
"bos_token": "<s>",
"do_lower_case": false,
"eos_token": "</s>",
"name_or_path": "sanchit-gandhi/wav2vec2-ctc-gs-black-box-tokenizer",
"pad_token": "<pad>",
"replace_word_delimiter_char": " ",
"special_tokens_map_file": null,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "<unk>",
"word_delimiter_token": "|"
}