Hugging Face's logo

monaf3
/
wav2vec2-large-mms-1b-turkish-colab

Model card Files Community
monaf3 commited on
Commit
9f0419b
•
1 Parent(s): d5e100d

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +47 -0
  4. vocab.json +73 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 70,
3
+ "<s>": 69
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
+ "67": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "68": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "69": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "70": {
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": "tur",
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tur": {
3
+ "[PAD]": 68,
4
+ "[UNK]": 67,
5
+ "_": 1,
6
+ "e": 2,
7
+ "g": 3,
8
+ "t": 4,
9
+ "|": 0,
10
+ "«": 5,
11
+ "»": 6,
12
+ "،": 7,
13
+ "؛": 8,
14
+ "؟": 9,
15
+ "ء": 10,
16
+ "آ": 11,
17
+ "أ": 12,
18
+ "ؤ": 13,
19
+ "إ": 14,
20
+ "ئ": 15,
21
+ "ا": 16,
22
+ "ب": 17,
23
+ "ة": 18,
24
+ "ت": 19,
25
+ "ث": 20,
26
+ "ج": 21,
27
+ "ح": 22,
28
+ "خ": 23,
29
+ "د": 24,
30
+ "ذ": 25,
31
+ "ر": 26,
32
+ "ز": 27,
33
+ "س": 28,
34
+ "ش": 29,
35
+ "ص": 30,
36
+ "ض": 31,
37
+ "ط": 32,
38
+ "ظ": 33,
39
+ "ع": 34,
40
+ "غ": 35,
41
+ "ـ": 36,
42
+ "ف": 37,
43
+ "ق": 38,
44
+ "ك": 39,
45
+ "ل": 40,
46
+ "م": 41,
47
+ "ن": 42,
48
+ "ه": 43,
49
+ "و": 44,
50
+ "ى": 45,
51
+ "ي": 46,
52
+ "ً": 47,
53
+ "ٌ": 48,
54
+ "ٍ": 49,
55
+ "َ": 50,
56
+ "ُ": 51,
57
+ "ِ": 52,
58
+ "ّ": 53,
59
+ "ْ": 54,
60
+ "ٰ": 55,
61
+ "چ": 56,
62
+ "ڨ": 57,
63
+ "ک": 58,
64
+ "ھ": 59,
65
+ "ی": 60,
66
+ "ۖ": 61,
67
+ "ۚ": 62,
68
+ "—": 63,
69
+ "☭": 64,
70
+ "ﺃ": 65,
71
+ "ﻻ": 66
72
+ }
73
+ }