Hugging Face's logo

ilyes25
/
wav2vec2-large-mms-1b-DZ-kabyle

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files Community
ilyes25 commited on
Commit
ffda52c
·
verified ·
1 Parent(s): 1f6c9b5

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +44 -42
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 44,
3
- "<s>": 43
4
  }
 
1
  {
2
+ "</s>": 46,
3
+ "<s>": 45
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "41": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "42": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "43": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "44": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "43": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "44": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "45": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "46": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -56,49 +56,51 @@
56
  "ڨ": 51
57
  },
58
  "fr": {
59
- "3": 1,
60
- "6": 2,
61
- "[PAD]": 42,
62
- "[UNK]": 41,
63
- "a": 3,
64
- "b": 4,
65
- "c": 5,
66
- "d": 6,
67
- "e": 7,
68
- "f": 8,
69
- "g": 9,
70
- "h": 10,
71
- "i": 11,
72
- "j": 12,
73
- "k": 13,
74
- "l": 14,
75
- "m": 15,
76
- "n": 16,
77
- "o": 17,
78
- "p": 18,
79
- "q": 19,
80
- "r": 20,
81
- "s": 21,
82
- "t": 22,
83
- "u": 23,
84
- "v": 24,
85
- "w": 25,
86
- "x": 26,
87
- "y": 27,
88
- "z": 28,
 
89
  "|": 0,
90
- "à": 29,
91
- "â": 30,
92
- "ç": 31,
93
- "è": 32,
94
- "é": 33,
95
- "ê": 34,
96
- "î": 35,
97
- "ï": 36,
98
- "ô": 37,
99
- "ù": 38,
100
- "û": 39,
101
- "œ": 40
 
102
  },
103
  "kab": {
104
  "$": 1,
 
56
  "ڨ": 51
57
  },
58
  "fr": {
59
+ "'": 1,
60
+ "3": 2,
61
+ "6": 3,
62
+ "[PAD]": 44,
63
+ "[UNK]": 43,
64
+ "a": 4,
65
+ "b": 5,
66
+ "c": 6,
67
+ "d": 7,
68
+ "e": 8,
69
+ "f": 9,
70
+ "g": 10,
71
+ "h": 11,
72
+ "i": 12,
73
+ "j": 13,
74
+ "k": 14,
75
+ "l": 15,
76
+ "m": 16,
77
+ "n": 17,
78
+ "o": 18,
79
+ "p": 19,
80
+ "q": 20,
81
+ "r": 21,
82
+ "s": 22,
83
+ "t": 23,
84
+ "u": 24,
85
+ "v": 25,
86
+ "w": 26,
87
+ "x": 27,
88
+ "y": 28,
89
+ "z": 29,
90
  "|": 0,
91
+ "à": 30,
92
+ "â": 31,
93
+ "ç": 32,
94
+ "è": 33,
95
+ "é": 34,
96
+ "ê": 35,
97
+ "î": 36,
98
+ "ï": 37,
99
+ "ô": 38,
100
+ "ù": 39,
101
+ "û": 40,
102
+ "œ": 41,
103
+ "’": 42
104
  },
105
  "kab": {
106
  "$": 1,