Hugging Face's logo

Thunpitcha
/
wav2vec2-base-thai-4-google-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Thunpitcha commited on
Commit
b74139a
•
1 Parent(s): 8b334a4

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 +86 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 85,
3
+ "<s>": 84
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
+ "82": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "83": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "84": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "85": {
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": null,
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 26,
3
+ "[PAD]": 83,
4
+ "[UNK]": 82,
5
+ "_": 46,
6
+ "a": 37,
7
+ "c": 65,
8
+ "e": 27,
9
+ "h": 67,
10
+ "i": 60,
11
+ "j": 15,
12
+ "n": 74,
13
+ "o": 57,
14
+ "s": 79,
15
+ "t": 54,
16
+ "|": 25,
17
+ "~": 49,
18
+ "ก": 36,
19
+ "ข": 4,
20
+ "ค": 55,
21
+ "ฆ": 3,
22
+ "ง": 52,
23
+ "จ": 61,
24
+ "ฉ": 68,
25
+ "ช": 58,
26
+ "ซ": 12,
27
+ "ฌ": 62,
28
+ "ญ": 59,
29
+ "ฎ": 6,
30
+ "ฏ": 22,
31
+ "ฐ": 29,
32
+ "ฑ": 80,
33
+ "ฒ": 69,
34
+ "ณ": 8,
35
+ "ด": 51,
36
+ "ต": 28,
37
+ "ถ": 33,
38
+ "ท": 43,
39
+ "ธ": 71,
40
+ "น": 13,
41
+ "บ": 21,
42
+ "ป": 18,
43
+ "ผ": 44,
44
+ "ฝ": 32,
45
+ "พ": 73,
46
+ "ฟ": 23,
47
+ "ภ": 64,
48
+ "ม": 19,
49
+ "ย": 30,
50
+ "ร": 5,
51
+ "ฤ": 53,
52
+ "ล": 66,
53
+ "ว": 1,
54
+ "ศ": 45,
55
+ "ษ": 2,
56
+ "ส": 77,
57
+ "ห": 40,
58
+ "ฬ": 24,
59
+ "อ": 9,
60
+ "ฮ": 76,
61
+ "ะ": 72,
62
+ "ั": 20,
63
+ "า": 38,
64
+ "ำ": 50,
65
+ "ิ": 16,
66
+ "ี": 75,
67
+ "ึ": 48,
68
+ "ื": 11,
69
+ "ุ": 39,
70
+ "ู": 31,
71
+ "เ": 35,
72
+ "แ": 10,
73
+ "โ": 70,
74
+ "ใ": 17,
75
+ "ไ": 42,
76
+ "ๅ": 47,
77
+ "ๆ": 34,
78
+ "็": 14,
79
+ "่": 56,
80
+ "้": 78,
81
+ "๊": 41,
82
+ "๋": 7,
83
+ "์": 63,
84
+ "ํ": 0,
85
+ "’": 81
86
+ }