perisolb commited on
Commit
d9b44cc
1 Parent(s): 78f9051

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 37,
3
+ "<s>": 36
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "[PAD]",
21
+ "unk_token": "[UNK]"
22
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "./",
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "special_tokens_map_file": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": " "
13
+ }
vocab.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 0,
3
+ "-": 1,
4
+ "[PAD]": 35,
5
+ "[UNK]": 34,
6
+ "_": 2,
7
+ "a": 3,
8
+ "b": 4,
9
+ "c": 5,
10
+ "d": 6,
11
+ "e": 7,
12
+ "f": 8,
13
+ "g": 9,
14
+ "h": 10,
15
+ "i": 11,
16
+ "j": 12,
17
+ "k": 13,
18
+ "l": 14,
19
+ "m": 15,
20
+ "n": 16,
21
+ "o": 17,
22
+ "p": 18,
23
+ "q": 19,
24
+ "r": 20,
25
+ "s": 21,
26
+ "t": 22,
27
+ "u": 23,
28
+ "v": 24,
29
+ "w": 25,
30
+ "x": 26,
31
+ "y": 27,
32
+ "z": 28,
33
+ " ": 29,
34
+ "å": 30,
35
+ "æ": 31,
36
+ "é": 32,
37
+ "ø": 33
38
+ }