NorHsangPha commited on
Commit
3eed201
1 Parent(s): 490b5b6

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 43,
3
+ "<s>": 42
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
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 ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "40": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "41": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "42": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "43": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
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": null,
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 41,
3
+ "[UNK]": 40,
4
+ "|": 0,
5
+ " ": 1,
6
+ "င": 2,
7
+ "တ": 3,
8
+ "ထ": 4,
9
+ "ပ": 5,
10
+ "မ": 6,
11
+ "ယ": 7,
12
+ "လ": 8,
13
+ "ဝ": 9,
14
+ "သ": 10,
15
+ "ဢ": 11,
16
+ "ိ": 12,
17
+ "ီ": 13,
18
+ "ု": 14,
19
+ "ူ": 15,
20
+ "ေ": 16,
21
+ "ဵ": 17,
22
+ "း": 18,
23
+ "်": 19,
24
+ "ျ": 20,
25
+ "ြ": 21,
26
+ "ွ": 22,
27
+ "ၢ": 23,
28
+ "ၵ": 24,
29
+ "ၶ": 25,
30
+ "ၸ": 26,
31
+ "ၺ": 27,
32
+ "ၼ": 28,
33
+ "ၽ": 29,
34
+ "ၾ": 30,
35
+ "ႁ": 31,
36
+ "ႂ": 32,
37
+ "ႃ": 33,
38
+ "ႄ": 34,
39
+ "ႅ": 35,
40
+ "ႆ": 36,
41
+ "ႇ": 37,
42
+ "ႈ": 38,
43
+ "ႉ": 39
44
+ }