Hugging Face's logo

tgrhn
/
wav2vec2-conformer-turkish-2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-conformer
Model card Files Metrics Community
tgrhn commited on
Commit
9be5cc9
·
verified ·
1 Parent(s): 3f139af

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +11 -12
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 43,
3
- "<s>": 42
4
  }
 
1
  {
2
+ "</s>": 42,
3
+ "<s>": 41
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "40": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "41": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "42": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "43": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "39": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "40": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "41": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "42": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "(": 1,
3
  ")": 2,
4
- "[PAD]": 41,
5
- "[UNK]": 40,
6
  "a": 3,
7
  "b": 4,
8
  "c": 5,
@@ -31,14 +31,13 @@
31
  "z": 28,
32
  "|": 0,
33
  "ç": 29,
34
- "é": 30,
35
- "ë": 31,
36
- "ö": 32,
37
- "ü": 33,
38
- "ğ": 34,
39
- "ı": 35,
40
- "ş": 36,
41
- "̇": 37,
42
- "’": 38,
43
- "…": 39
44
  }
 
1
  {
2
  "(": 1,
3
  ")": 2,
4
+ "[PAD]": 40,
5
+ "[UNK]": 39,
6
  "a": 3,
7
  "b": 4,
8
  "c": 5,
 
31
  "z": 28,
32
  "|": 0,
33
  "ç": 29,
34
+ "ë": 30,
35
+ "ö": 31,
36
+ "ü": 32,
37
+ "ğ": 33,
38
+ "ı": 34,
39
+ "ş": 35,
40
+ "̇": 36,
41
+ "’": 37,
42
+ "…": 38
 
43
  }