Hugging Face's logo

Sajjo
/
wav2vec2-large-mms-1b-tamil-v1

Transformers
Inference Endpoints
Model card Files Community
Sajjo commited on
Commit
4800b6a
•
1 Parent(s): 9ede42e

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +51 -85
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 87,
3
- "<s>": 86
4
  }
 
1
  {
2
+ "</s>": 53,
3
+ "<s>": 52
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "84": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "85": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "86": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "87": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "50": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "51": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "52": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "53": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,90 +1,56 @@
1
  {
2
  "ta": {
3
- "[PAD]": 85,
4
- "[UNK]": 84,
5
- "\\": 1,
6
- "a": 2,
7
- "b": 3,
8
- "c": 4,
9
- "d": 5,
10
- "e": 6,
11
- "f": 7,
12
- "g": 8,
13
- "h": 9,
14
- "i": 10,
15
- "j": 11,
16
- "k": 12,
17
- "l": 13,
18
- "m": 14,
19
- "n": 15,
20
- "o": 16,
21
- "p": 17,
22
- "q": 18,
23
- "r": 19,
24
- "s": 20,
25
- "t": 21,
26
- "u": 22,
27
- "v": 23,
28
- "w": 24,
29
- "x": 25,
30
- "y": 26,
31
- "z": 27,
32
  "|": 0,
33
- "½": 28,
34
- "¾": 29,
35
- "á": 30,
36
- "é": 31,
37
- "š": 32,
38
- "அ": 33,
39
- "ஆ": 34,
40
- "இ": 35,
41
- "ஈ": 36,
42
- "உ": 37,
43
- "ஊ": 38,
44
- "எ": 39,
45
- "ஏ": 40,
46
- "ஐ": 41,
47
- "ஒ": 42,
48
- "ஓ": 43,
49
- "ஔ": 44,
50
- "க": 45,
51
- "ங": 46,
52
- "ச": 47,
53
- "ஜ": 48,
54
- "ஞ": 49,
55
- "ட": 50,
56
- "ண": 51,
57
- "த": 52,
58
- "ந": 53,
59
- "ன": 54,
60
- "ப": 55,
61
- "ம": 56,
62
- "ய": 57,
63
- "ர": 58,
64
- "ற": 59,
65
- "ல": 60,
66
- "ள": 61,
67
- "ழ": 62,
68
- "வ": 63,
69
- "ஷ": 64,
70
- "ஸ": 65,
71
- "ஹ": 66,
72
- "ா": 67,
73
- "ி": 68,
74
- "ீ": 69,
75
- "ு": 70,
76
- "ூ": 71,
77
- "ெ": 72,
78
- "ே": 73,
79
- "ை": 74,
80
- "ொ": 75,
81
- "ோ": 76,
82
- "ௌ": 77,
83
- "்": 78,
84
- "ௗ": 79,
85
- "ഥ": 80,
86
- "–": 81,
87
- "●": 82,
88
- "◯": 83
89
  }
90
  }
 
1
  {
2
  "ta": {
3
+ "[PAD]": 51,
4
+ "[UNK]": 50,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "|": 0,
6
+ "அ": 1,
7
+ "ஆ": 2,
8
+ "இ": 3,
9
+ "ஈ": 4,
10
+ "உ": 5,
11
+ "ஊ": 6,
12
+ "எ": 7,
13
+ "ஏ": 8,
14
+ "ஐ": 9,
15
+ "ஒ": 10,
16
+ "ஓ": 11,
17
+ "ஔ": 12,
18
+ "க": 13,
19
+ "ங": 14,
20
+ "ச": 15,
21
+ "ஜ": 16,
22
+ "ஞ": 17,
23
+ "ட": 18,
24
+ "ண": 19,
25
+ "த": 20,
26
+ "ந": 21,
27
+ "ன": 22,
28
+ "ப": 23,
29
+ "ம": 24,
30
+ "ய": 25,
31
+ "ர": 26,
32
+ "ற": 27,
33
+ "ல": 28,
34
+ "ள": 29,
35
+ "ழ": 30,
36
+ "வ": 31,
37
+ "ஷ": 32,
38
+ "ஸ": 33,
39
+ "ஹ": 34,
40
+ "ா": 35,
41
+ "ி": 36,
42
+ "ீ": 37,
43
+ "ு": 38,
44
+ "ூ": 39,
45
+ "ெ": 40,
46
+ "ே": 41,
47
+ "ை": 42,
48
+ "ொ": 43,
49
+ "ோ": 44,
50
+ "ௌ": 45,
51
+ "்": 46,
52
+ "ௗ": 47,
53
+ "ഥ": 48,
54
+ "◯": 49
 
 
 
 
 
 
 
55
  }
56
  }