Taeham commited on
Commit
f5f1b29
·
1 Parent(s): 3694aef

add tokenizer

Browse files
Files changed (2) hide show
  1. .gitignore +1 -0
  2. tokenizer_config.json +1 -1
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}