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
a7b790b
•
1 Parent(s): 6799feb

Upload tokenizer

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