Hugging Face's logo

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

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
Thunpitcha commited on
Commit
eb4a629
·
1 Parent(s): 3570d5a

Upload tokenizer

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