lm_wiki / tokenizer_config.json
mazharsaif's picture
add tokenizer
09916a2
raw
history blame
599 Bytes
{
"bos_token": "<s>",
"do_lower_case": false,
"do_normalize": true,
"eos_token": "</s>",
"name_or_path": "facebook/data2vec-audio-base-960h",
"pad_token": "<pad>",
"processor_class": "Wav2Vec2Processor",
"replace_word_delimiter_char": " ",
"return_attention_mask": false,
"special_tokens_map_file": "/home/patrick/.cache/huggingface/transformers/60230682499b8486f2a3109ba26ac7395fd4eba61426f05432329ccbfac7c190.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd",
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "<unk>",
"word_delimiter_token": "|"
}