Hugging Face's logo

HuyenNguyen
/
wav2vec2-large-mms-1b-turkish-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
HuyenNguyen commited on
Commit
81c4d5a
•
1 Parent(s): d81077d

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +1 -1
  3. vocab.json +67 -65
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 90,
3
- "<s>": 89
4
  }
 
1
  {
2
+ "</s>": 92,
3
+ "<s>": 91
4
  }
tokenizer_config.json CHANGED
@@ -6,7 +6,7 @@
6
  "model_max_length": 1000000000000000019884624838656,
7
  "pad_token": "[PAD]",
8
  "replace_word_delimiter_char": " ",
9
- "target_lang": "tur",
10
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
  "unk_token": "[UNK]",
12
  "word_delimiter_token": "|"
 
6
  "model_max_length": 1000000000000000019884624838656,
7
  "pad_token": "[PAD]",
8
  "replace_word_delimiter_char": " ",
9
+ "target_lang": "vi",
10
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
  "unk_token": "[UNK]",
12
  "word_delimiter_token": "|"
vocab.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "tur": {
3
- "[PAD]": 88,
4
- "[UNK]": 87,
5
  "a": 1,
6
  "b": 2,
7
  "c": 3,
@@ -27,67 +27,69 @@
27
  "|": 0,
28
  "à": 23,
29
  "á": 24,
30
- "ã": 25,
31
- "è": 26,
32
- "é": 27,
33
- "ê": 28,
34
- "ì": 29,
35
- "í": 30,
36
- "ò": 31,
37
- "ó": 32,
38
- "õ": 33,
39
- "ù": 34,
40
- "ú": 35,
41
- "ý": 36,
42
- "ă": 37,
43
- "đ": 38,
44
- "ĩ": 39,
45
- "ũ": 40,
46
- "ơ": 41,
47
- "ư": 42,
48
- "ạ": 43,
49
- "ả": 44,
50
- "ấ": 45,
51
- "ầ": 46,
52
- "ẩ": 47,
53
- "ẫ": 48,
54
- "ậ": 49,
55
- "ắ": 50,
56
- "ằ": 51,
57
- "ẳ": 52,
58
- "ẵ": 53,
59
- "ặ": 54,
60
- "ẹ": 55,
61
- "ẻ": 56,
62
- "ẽ": 57,
63
- "ế": 58,
64
- "ề": 59,
65
- "ể": 60,
66
- "ễ": 61,
67
- "ệ": 62,
68
- "ỉ": 63,
69
- "ị": 64,
70
- "ọ": 65,
71
- "ỏ": 66,
72
- "ố": 67,
73
- "ồ": 68,
74
- "ổ": 69,
75
- "ỗ": 70,
76
- "ộ": 71,
77
- "ớ": 72,
78
- "ờ": 73,
79
- "ở": 74,
80
- "ỡ": 75,
81
- "ợ": 76,
82
- "ụ": 77,
83
- "ủ": 78,
84
- "ứ": 79,
85
- "ừ": 80,
86
- "ử": 81,
87
- "ữ": 82,
88
- "ự": 83,
89
- "ỳ": 84,
90
- "ỷ": 85,
91
- "ỹ": 86
 
 
92
  }
93
  }
 
1
  {
2
+ "vi": {
3
+ "[PAD]": 90,
4
+ "[UNK]": 89,
5
  "a": 1,
6
  "b": 2,
7
  "c": 3,
 
27
  "|": 0,
28
  "à": 23,
29
  "á": 24,
30
+ "â": 25,
31
+ "ã": 26,
32
+ "è": 27,
33
+ "é": 28,
34
+ "ê": 29,
35
+ "ì": 30,
36
+ "í": 31,
37
+ "ò": 32,
38
+ "ó": 33,
39
+ "ô": 34,
40
+ "õ": 35,
41
+ "ù": 36,
42
+ "ú": 37,
43
+ "ý": 38,
44
+ "ă": 39,
45
+ "đ": 40,
46
+ "ĩ": 41,
47
+ "ũ": 42,
48
+ "ơ": 43,
49
+ "ư": 44,
50
+ "ạ": 45,
51
+ "ả": 46,
52
+ "ấ": 47,
53
+ "ầ": 48,
54
+ "ẩ": 49,
55
+ "ẫ": 50,
56
+ "ậ": 51,
57
+ "ắ": 52,
58
+ "ằ": 53,
59
+ "ẳ": 54,
60
+ "ẵ": 55,
61
+ "ặ": 56,
62
+ "ẹ": 57,
63
+ "ẻ": 58,
64
+ "ẽ": 59,
65
+ "ế": 60,
66
+ "ề": 61,
67
+ "ể": 62,
68
+ "ễ": 63,
69
+ "ệ": 64,
70
+ "ỉ": 65,
71
+ "ị": 66,
72
+ "ọ": 67,
73
+ "ỏ": 68,
74
+ "ố": 69,
75
+ "ồ": 70,
76
+ "ổ": 71,
77
+ "ỗ": 72,
78
+ "ộ": 73,
79
+ "ớ": 74,
80
+ "ờ": 75,
81
+ "ở": 76,
82
+ "ỡ": 77,
83
+ "ợ": 78,
84
+ "ụ": 79,
85
+ "ủ": 80,
86
+ "ứ": 81,
87
+ "ừ": 82,
88
+ "ử": 83,
89
+ "ữ": 84,
90
+ "ự": 85,
91
+ "ỳ": 86,
92
+ "ỷ": 87,
93
+ "ỹ": 88
94
  }
95
  }