Hugging Face's logo

davidilag
/
wav2vec2-xls-r-1b-danish-12h-6k-steps

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
davidilag commited on
Commit
5f22c10
·
verified ·
1 Parent(s): 849ca13

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +36 -34
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 39,
3
- "<s>": 38
4
  }
 
1
  {
2
+ "</s>": 41,
3
+ "<s>": 40
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "36": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "37": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "38": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "39": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "38": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "39": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "40": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "41": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,40 +1,42 @@
1
  {
2
- "'": 19,
3
- "(": 3,
4
- ")": 5,
5
- "*": 1,
6
- "[PAD]": 37,
7
- "[UNK]": 36,
8
- "a": 17,
9
- "b": 6,
10
- "c": 4,
11
- "d": 9,
12
- "e": 22,
13
- "f": 15,
14
- "g": 23,
15
  "h": 10,
16
  "i": 24,
17
- "j": 34,
18
- "k": 2,
19
- "l": 35,
20
- "m": 18,
21
- "n": 11,
22
- "o": 8,
23
- "p": 30,
24
- "r": 20,
25
- "s": 31,
26
- "t": 33,
27
- "u": 27,
28
- "v": 25,
 
29
  "w": 32,
30
  "x": 28,
31
- "y": 13,
32
- "|": 16,
33
- "á": 21,
34
- "é": 14,
35
- "í": 12,
36
- "ó": 7,
37
- "ú": 29,
38
- "–": 0,
39
- "’": 26
 
 
 
 
40
  }
 
1
  {
2
+ "'": 30,
3
+ "[PAD]": 39,
4
+ "[UNK]": 38,
5
+ "a": 31,
6
+ "b": 7,
7
+ "c": 12,
8
+ "d": 4,
9
+ "e": 34,
10
+ "f": 23,
11
+ "g": 15,
 
 
 
12
  "h": 10,
13
  "i": 24,
14
+ "j": 3,
15
+ "k": 8,
16
+ "l": 9,
17
+ "m": 14,
18
+ "n": 33,
19
+ "o": 22,
20
+ "p": 37,
21
+ "q": 27,
22
+ "r": 25,
23
+ "s": 0,
24
+ "t": 18,
25
+ "u": 21,
26
+ "v": 16,
27
  "w": 32,
28
  "x": 28,
29
+ "y": 20,
30
+ "z": 17,
31
+ "|": 13,
32
+ "«": 11,
33
+ "»": 5,
34
+ "å": 36,
35
+ "æ": 35,
36
+ "é": 6,
37
+ "í": 19,
38
+ "ó": 2,
39
+ "ø": 26,
40
+ "–": 29,
41
+ "—": 1
42
  }