Hugging Face's logo

gweltou
/
mHuBERT-147-br

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Breton
hubert
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
gweltou commited on
Commit
ebab3d4
·
verified ·
1 Parent(s): a7b790b

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +53 -56
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 57,
3
- "<s>": 56
4
  }
 
1
  {
2
+ "</s>": 54,
3
+ "<s>": 53
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "54": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "55": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "56": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "57": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "51": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "52": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "53": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "54": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,58 +1,55 @@
1
  {
2
- "'": 53,
3
- "3": 24,
4
- "A": 13,
5
- "E": 6,
6
- "I": 31,
7
- "O": 0,
8
- "S": 34,
9
- "X": 37,
10
- "Z": 14,
11
- "[PAD]": 55,
12
- "[UNK]": 54,
13
- "a": 30,
14
- "b": 28,
15
- "c": 32,
16
- "d": 27,
17
- "e": 19,
18
- "f": 52,
19
- "g": 1,
20
- "h": 39,
21
- "i": 36,
22
- "j": 18,
23
- "k": 43,
24
- "l": 44,
25
- "m": 38,
26
- "n": 20,
27
- "o": 33,
28
- "p": 3,
29
- "q": 16,
30
- "r": 9,
31
- "s": 10,
32
- "t": 5,
33
- "u": 41,
34
- "v": 21,
35
- "w": 49,
36
- "x": 46,
37
- "y": 17,
38
- "z": 22,
39
- "|": 35,
40
- "Ù": 42,
41
- "à": 48,
42
- "á": 8,
43
- "â": 15,
44
- "ã": 45,
45
- "ç": 2,
46
- "è": 51,
47
- "é": 29,
48
- "ê": 4,
49
- "ë": 7,
50
- "ñ": 12,
51
- "ô": 47,
52
- "ö": 23,
53
- "ø": 50,
54
- "ù": 25,
55
- "û": 40,
56
- "ü": 11,
57
- "ı": 26
58
  }
 
1
  {
2
+ "'": 29,
3
+ "3": 36,
4
+ "A": 12,
5
+ "E": 18,
6
+ "I": 22,
7
+ "O": 45,
8
+ "S": 32,
9
+ "X": 11,
10
+ "Z": 46,
11
+ "[PAD]": 52,
12
+ "[UNK]": 51,
13
+ "a": 20,
14
+ "b": 25,
15
+ "c": 38,
16
+ "d": 23,
17
+ "e": 35,
18
+ "f": 0,
19
+ "g": 40,
20
+ "h": 31,
21
+ "i": 24,
22
+ "j": 3,
23
+ "k": 34,
24
+ "l": 49,
25
+ "m": 16,
26
+ "n": 13,
27
+ "o": 4,
28
+ "p": 1,
29
+ "q": 17,
30
+ "r": 48,
31
+ "s": 8,
32
+ "t": 50,
33
+ "u": 26,
34
+ "v": 2,
35
+ "w": 37,
36
+ "x": 27,
37
+ "y": 15,
38
+ "z": 5,
39
+ "|": 47,
40
+ "Ù": 43,
41
+ "à": 19,
42
+ "á": 42,
43
+ "â": 7,
44
+ "ç": 6,
45
+ "è": 33,
46
+ "é": 9,
47
+ "ê": 21,
48
+ "ë": 10,
49
+ "ñ": 41,
50
+ "ô": 30,
51
+ "ö": 39,
52
+ "ù": 44,
53
+ "û": 28,
54
+ "ü": 14
 
 
 
55
  }