dmatekenya commited on
Commit
4a49a9d
1 Parent(s): 10c13e6

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 48,
3
+ "<s>": 47
4
+ }
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "45": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "46": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "47": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "48": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": "nya",
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nya": {
3
+ "\t": 0,
4
+ "$": 2,
5
+ "(": 3,
6
+ ")": 4,
7
+ "/": 5,
8
+ "0": 6,
9
+ "1": 7,
10
+ "2": 8,
11
+ "3": 9,
12
+ "4": 10,
13
+ "5": 11,
14
+ "6": 12,
15
+ "7": 13,
16
+ "8": 14,
17
+ "9": 15,
18
+ "[PAD]": 46,
19
+ "[UNK]": 45,
20
+ "a": 16,
21
+ "b": 17,
22
+ "c": 18,
23
+ "d": 19,
24
+ "e": 20,
25
+ "f": 21,
26
+ "g": 22,
27
+ "h": 23,
28
+ "i": 24,
29
+ "j": 25,
30
+ "k": 26,
31
+ "l": 27,
32
+ "m": 28,
33
+ "n": 29,
34
+ "o": 30,
35
+ "p": 31,
36
+ "q": 32,
37
+ "r": 33,
38
+ "s": 34,
39
+ "t": 35,
40
+ "u": 36,
41
+ "v": 37,
42
+ "w": 38,
43
+ "x": 39,
44
+ "y": 40,
45
+ "z": 41,
46
+ "|": 1,
47
+ "’": 42,
48
+ "…": 43,
49
+ "": 44
50
+ }
51
+ }