ljcamargo commited on
Commit
3d049ae
1 Parent(s): e9a260c

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +13 -0
  3. vocab.json +39 -0
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "target_lang": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 23,
3
+ "[PAD]": 36,
4
+ "[UNK]": 35,
5
+ "a": 30,
6
+ "b": 34,
7
+ "c": 25,
8
+ "d": 5,
9
+ "e": 26,
10
+ "f": 19,
11
+ "g": 13,
12
+ "h": 12,
13
+ "i": 22,
14
+ "j": 17,
15
+ "k": 32,
16
+ "l": 27,
17
+ "m": 33,
18
+ "n": 21,
19
+ "o": 10,
20
+ "p": 0,
21
+ "q": 7,
22
+ "r": 24,
23
+ "s": 14,
24
+ "t": 11,
25
+ "u": 20,
26
+ "v": 18,
27
+ "w": 4,
28
+ "x": 3,
29
+ "y": 15,
30
+ "z": 8,
31
+ "|": 29,
32
+ "á": 9,
33
+ "é": 1,
34
+ "í": 2,
35
+ "ñ": 6,
36
+ "ó": 28,
37
+ "ú": 31,
38
+ "ü": 16
39
+ }