TheAIchemist13 commited on
Commit
a3dcc06
·
1 Parent(s): 83b9a27

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +28 -4
  2. tokenizer_config.json +0 -1
special_tokens_map.json CHANGED
@@ -1,6 +1,30 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "pad_token": "<pad>",
5
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": true,
5
+ "normalized": false,
6
+ "rstrip": true,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": true,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
  }
tokenizer_config.json CHANGED
@@ -43,7 +43,6 @@
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
- "tokenizer_file": null,
47
  "unk_token": "<unk>",
48
  "word_delimiter_token": "|"
49
  }
 
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
46
  "unk_token": "<unk>",
47
  "word_delimiter_token": "|"
48
  }