Hugging Face's logo

Thunpitcha
/
wav2vec2-base-thai-demo-google-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Thunpitcha commited on
Commit
3570d5a
•
1 Parent(s): a7a8578

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +69 -78
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 85,
3
- "<s>": 84
4
  }
 
1
  {
2
+ "</s>": 76,
3
+ "<s>": 75
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "82": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "83": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "84": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": true,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "85": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "73": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "74": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "75": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": true,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "76": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
vocab.json CHANGED
@@ -1,86 +1,77 @@
1
  {
2
  "'": 4,
3
- "[PAD]": 83,
4
- "[UNK]": 82,
5
- "_": 57,
6
- "c": 74,
7
- "e": 47,
8
- "i": 35,
9
- "k": 63,
10
- "l": 62,
11
- "m": 30,
12
- "n": 60,
13
- "o": 56,
14
- "r": 42,
15
- "y": 15,
16
- "|": 48,
17
- "~": 16,
18
  "ก": 0,
19
- "ข": 67,
20
- "ค": 64,
21
- "ฆ": 20,
22
- "ง": 31,
23
- "จ": 65,
24
- "ฉ": 29,
25
- "ช": 39,
26
- "ซ": 26,
27
- "ฌ": 24,
28
- "ญ": 18,
29
- "ฎ": 27,
30
- "ฏ": 81,
31
- "ฐ": 51,
32
- "ฑ": 25,
33
- "ฒ": 70,
34
  "ณ": 1,
35
- "ด": 76,
36
- "ต": 53,
37
- "ถ": 78,
38
  "ท": 3,
39
- "ธ": 79,
40
- "น": 28,
41
- "บ": 13,
42
- "ป": 21,
43
- "ผ": 77,
44
- "ฝ": 12,
45
- "พ": 38,
46
- "ฟ": 34,
47
- "ภ": 80,
48
- "ม": 54,
49
- "ย": 22,
50
- "ร": 49,
51
- "ฤ": 68,
52
- "ล": 41,
53
- "ว": 75,
54
- "ศ": 52,
55
- "ษ": 44,
56
- "ส": 72,
57
- "ห": 50,
58
  "ฬ": 2,
59
- "อ": 59,
60
- "ฮ": 32,
61
- "ะ": 55,
62
- "ั": 19,
63
- "า": 10,
64
- "ำ": 58,
65
- "ิ": 17,
66
- "ี": 45,
67
- "ึ": 23,
68
- "ื": 33,
69
- "ุ": 11,
70
- "ู": 36,
71
- "เ": 73,
72
- "แ": 40,
73
- "โ": 37,
74
- "ใ": 61,
75
- "ไ": 8,
76
- "ๅ": 66,
77
- "ๆ": 46,
78
- "็": 14,
79
- "่": 6,
80
- "้": 69,
81
  "๊": 7,
82
- "๋": 9,
83
- "์": 43,
84
- "ํ": 5,
85
- "’": 71
86
  }
 
1
  {
2
  "'": 4,
3
+ "[PAD]": 74,
4
+ "[UNK]": 73,
5
+ "a": 51,
6
+ "h": 60,
7
+ "j": 35,
8
+ "n": 54,
9
+ "o": 50,
10
+ "|": 42,
11
+ "~": 14,
 
 
 
 
 
 
12
  "ก": 0,
13
+ "ข": 58,
14
+ "ค": 56,
15
+ "ฆ": 18,
16
+ "ง": 27,
17
+ "จ": 57,
18
+ "ฉ": 26,
19
+ "ช": 34,
20
+ "ซ": 23,
21
+ "ญ": 17,
22
+ "ฎ": 24,
23
+ "ฏ": 72,
24
+ "ฐ": 45,
25
+ "ฑ": 22,
26
+ "ฒ": 62,
 
27
  "ณ": 1,
28
+ "ด": 67,
29
+ "ต": 47,
30
+ "ถ": 69,
31
  "ท": 3,
32
+ "ธ": 70,
33
+ "น": 25,
34
+ "บ": 12,
35
+ "ป": 19,
36
+ "ผ": 68,
37
+ "ฝ": 11,
38
+ "พ": 32,
39
+ "ฟ": 30,
40
+ "ภ": 71,
41
+ "ม": 48,
42
+ "ย": 20,
43
+ "ร": 43,
44
+ "ฤ": 59,
45
+ "ล": 37,
46
+ "ว": 66,
47
+ "ศ": 46,
48
+ "ษ": 39,
49
+ "ส": 63,
50
+ "ห": 44,
51
  "ฬ": 2,
52
+ "อ": 53,
53
+ "ฮ": 28,
54
+ "ะ": 49,
55
+ "ั": 16,
56
+ "า": 9,
57
+ "ำ": 52,
58
+ "ิ": 15,
59
+ "ี": 40,
60
+ "ึ": 21,
61
+ "ื": 29,
62
+ "ุ": 10,
63
+ "ู": 31,
64
+ "เ": 65,
65
+ "แ": 36,
66
+ "โ": 33,
67
+ "ใ": 55,
68
+ "ไ": 6,
69
+ "ๆ": 41,
70
+ "็": 13,
71
+ "่": 5,
72
+ "้": 61,
 
73
  "๊": 7,
74
+ "๋": 8,
75
+ "์": 38,
76
+ "’": 64
 
77
  }