ntsema commited on
Commit
ce61bd9
1 Parent(s): 7ac670f

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 63,
3
+ "<s>": 62
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 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "./",
6
+ "pad_token": "[PAD]",
7
+ "replace_word_delimiter_char": " ",
8
+ "special_tokens_map_file": null,
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 61,
3
+ "[UNK]": 60,
4
+ "a": 1,
5
+ "aː": 56,
6
+ "b": 2,
7
+ "c": 3,
8
+ "d": 4,
9
+ "e": 5,
10
+ "f": 6,
11
+ "g": 7,
12
+ "h": 8,
13
+ "i": 9,
14
+ "j": 10,
15
+ "k": 11,
16
+ "l": 12,
17
+ "m": 13,
18
+ "n": 14,
19
+ "o": 15,
20
+ "p": 16,
21
+ "q": 17,
22
+ "r": 18,
23
+ "s": 19,
24
+ "t": 20,
25
+ "t͡ʃ": 57,
26
+ "u": 21,
27
+ "v": 22,
28
+ "w": 23,
29
+ "x": 24,
30
+ "y": 25,
31
+ "z": 26,
32
+ "|": 0,
33
+ "æ": 27,
34
+ "ð": 28,
35
+ "ø": 29,
36
+ "ü": 30,
37
+ "ŋ": 31,
38
+ "œ": 32,
39
+ "ɐ": 33,
40
+ "ɑ": 34,
41
+ "ɒ": 35,
42
+ "ɔ": 36,
43
+ "ɕ": 37,
44
+ "ə": 38,
45
+ "ɛ": 39,
46
+ "ɜ": 40,
47
+ "ɡ": 41,
48
+ "ɣ": 42,
49
+ "ɨ": 43,
50
+ "ɪ": 44,
51
+ "ɯ": 45,
52
+ "ɵ": 46,
53
+ "ɸ": 47,
54
+ "ʃ": 48,
55
+ "ʉ": 49,
56
+ "ʊ": 50,
57
+ "ʌ": 51,
58
+ "ʐ": 52,
59
+ "ʑ": 53,
60
+ "ʒ": 54,
61
+ "ʔ": 55,
62
+ "β": 58,
63
+ "θ": 59
64
+ }