Hugging Face's logo

Thienpkae
/
wav2vec2-large-xls-r-vi-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Thienpkae commited on
Commit
59774cc
•
1 Parent(s): 89583b6

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -4
  2. special_tokens_map.json +6 -22
  3. tokenizer_config.json +47 -13
  4. vocab.json +93 -93
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
- {
2
- "</s>": 92,
3
- "<s>": 91
4
- }
 
1
+ {
2
+ "</s>": 92,
3
+ "<s>": 91
4
+ }
special_tokens_map.json CHANGED
@@ -1,22 +1,6 @@
1
- {
2
- "additional_special_tokens": [
3
- {
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "</s>",
12
- "lstrip": false,
13
- "normalized": true,
14
- "rstrip": false,
15
- "single_word": false
16
- }
17
- ],
18
- "bos_token": "<s>",
19
- "eos_token": "</s>",
20
- "pad_token": "[PAD]",
21
- "unk_token": "[UNK]"
22
- }
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_config.json CHANGED
@@ -1,13 +1,47 @@
1
- {
2
- "bos_token": "<s>",
3
- "clean_up_tokenization_spaces": true,
4
- "do_lower_case": false,
5
- "eos_token": "</s>",
6
- "model_max_length": 1000000000000000019884624838656,
7
- "pad_token": "[PAD]",
8
- "replace_word_delimiter_char": " ",
9
- "target_lang": null,
10
- "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
- "unk_token": "[UNK]",
12
- "word_delimiter_token": "|"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "89": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "90": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "91": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
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 CHANGED
@@ -1,93 +1,93 @@
1
- {
2
- "[PAD]": 90,
3
- "[UNK]": 89,
4
- "a": 1,
5
- "b": 2,
6
- "c": 3,
7
- "d": 4,
8
- "e": 5,
9
- "g": 6,
10
- "h": 7,
11
- "i": 8,
12
- "j": 9,
13
- "k": 10,
14
- "l": 11,
15
- "m": 12,
16
- "n": 13,
17
- "o": 14,
18
- "p": 15,
19
- "q": 16,
20
- "r": 17,
21
- "s": 18,
22
- "t": 19,
23
- "u": 20,
24
- "v": 21,
25
- "x": 22,
26
- "y": 23,
27
- "|": 0,
28
- "à": 24,
29
- "á": 25,
30
- "â": 26,
31
- "ã": 27,
32
- "è": 28,
33
- "é": 29,
34
- "ê": 30,
35
- "ì": 31,
36
- "í": 32,
37
- "ò": 33,
38
- "ó": 34,
39
- "ô": 35,
40
- "õ": 36,
41
- "ù": 37,
42
- "ú": 38,
43
- "ý": 39,
44
- "ă": 40,
45
- "đ": 41,
46
- "ĩ": 42,
47
- "ũ": 43,
48
- "ơ": 44,
49
- "ư": 45,
50
- "ạ": 46,
51
- "ả": 47,
52
- "ấ": 48,
53
- "ầ": 49,
54
- "ẩ": 50,
55
- "ẫ": 51,
56
- "ậ": 52,
57
- "ắ": 53,
58
- "ằ": 54,
59
- "ẳ": 55,
60
- "ặ": 56,
61
- "ẹ": 57,
62
- "ẻ": 58,
63
- "ẽ": 59,
64
- "ế": 60,
65
- "ề": 61,
66
- "ể": 62,
67
- "ễ": 63,
68
- "ệ": 64,
69
- "ỉ": 65,
70
- "ị": 66,
71
- "ọ": 67,
72
- "ỏ": 68,
73
- "ố": 69,
74
- "ồ": 70,
75
- "ổ": 71,
76
- "ỗ": 72,
77
- "ộ": 73,
78
- "ớ": 74,
79
- "ờ": 75,
80
- "ở": 76,
81
- "ỡ": 77,
82
- "ợ": 78,
83
- "ụ": 79,
84
- "ủ": 80,
85
- "ứ": 81,
86
- "ừ": 82,
87
- "ử": 83,
88
- "ữ": 84,
89
- "ự": 85,
90
- "ỳ": 86,
91
- "ỷ": 87,
92
- "ỹ": 88
93
- }
 
1
+ {
2
+ "[PAD]": 90,
3
+ "[UNK]": 89,
4
+ "a": 1,
5
+ "b": 2,
6
+ "c": 3,
7
+ "d": 4,
8
+ "e": 5,
9
+ "g": 6,
10
+ "h": 7,
11
+ "i": 8,
12
+ "j": 9,
13
+ "k": 10,
14
+ "l": 11,
15
+ "m": 12,
16
+ "n": 13,
17
+ "o": 14,
18
+ "p": 15,
19
+ "q": 16,
20
+ "r": 17,
21
+ "s": 18,
22
+ "t": 19,
23
+ "u": 20,
24
+ "v": 21,
25
+ "x": 22,
26
+ "y": 23,
27
+ "|": 0,
28
+ "à": 24,
29
+ "á": 25,
30
+ "â": 26,
31
+ "ã": 27,
32
+ "è": 28,
33
+ "é": 29,
34
+ "ê": 30,
35
+ "ì": 31,
36
+ "í": 32,
37
+ "ò": 33,
38
+ "ó": 34,
39
+ "ô": 35,
40
+ "õ": 36,
41
+ "ù": 37,
42
+ "ú": 38,
43
+ "ý": 39,
44
+ "ă": 40,
45
+ "đ": 41,
46
+ "ĩ": 42,
47
+ "ũ": 43,
48
+ "ơ": 44,
49
+ "ư": 45,
50
+ "ạ": 46,
51
+ "ả": 47,
52
+ "ấ": 48,
53
+ "ầ": 49,
54
+ "ẩ": 50,
55
+ "ẫ": 51,
56
+ "ậ": 52,
57
+ "ắ": 53,
58
+ "ằ": 54,
59
+ "ẳ": 55,
60
+ "ặ": 56,
61
+ "ẹ": 57,
62
+ "ẻ": 58,
63
+ "ẽ": 59,
64
+ "ế": 60,
65
+ "ề": 61,
66
+ "ể": 62,
67
+ "ễ": 63,
68
+ "ệ": 64,
69
+ "ỉ": 65,
70
+ "ị": 66,
71
+ "ọ": 67,
72
+ "ỏ": 68,
73
+ "ố": 69,
74
+ "ồ": 70,
75
+ "ổ": 71,
76
+ "ỗ": 72,
77
+ "ộ": 73,
78
+ "ớ": 74,
79
+ "ờ": 75,
80
+ "ở": 76,
81
+ "ỡ": 77,
82
+ "ợ": 78,
83
+ "ụ": 79,
84
+ "ủ": 80,
85
+ "ứ": 81,
86
+ "ừ": 82,
87
+ "ử": 83,
88
+ "ữ": 84,
89
+ "ự": 85,
90
+ "ỳ": 86,
91
+ "ỷ": 87,
92
+ "ỹ": 88
93
+ }