Hugging Face's logo

tgrhn
/
wav2vec2-turkish-2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Turkish
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
tgrhn commited on
Commit
39dc3fe
•
1 Parent(s): 4d0a656

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +22 -21
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 41,
3
- "<s>": 40
4
  }
 
1
  {
2
+ "</s>": 42,
3
+ "<s>": 41
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "38": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "39": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "40": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "41": {
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]": 39,
5
- "[UNK]": 38,
6
  "a": 3,
7
  "b": 4,
8
  "c": 5,
@@ -19,24 +19,25 @@
19
  "n": 16,
20
  "o": 17,
21
  "p": 18,
22
- "r": 19,
23
- "s": 20,
24
- "t": 21,
25
- "u": 22,
26
- "v": 23,
27
- "w": 24,
28
- "x": 25,
29
- "y": 26,
30
- "z": 27,
 
31
  "|": 0,
32
- "ç": 28,
33
- "ë": 29,
34
- "ö": 30,
35
- "ü": 31,
36
- "ğ": 32,
37
- "ı": 33,
38
- "ş": 34,
39
- "̇": 35,
40
- "’": 36,
41
- "…": 37
42
  }
 
1
  {
2
  "(": 1,
3
  ")": 2,
4
+ "[PAD]": 40,
5
+ "[UNK]": 39,
6
  "a": 3,
7
  "b": 4,
8
  "c": 5,
 
19
  "n": 16,
20
  "o": 17,
21
  "p": 18,
22
+ "q": 19,
23
+ "r": 20,
24
+ "s": 21,
25
+ "t": 22,
26
+ "u": 23,
27
+ "v": 24,
28
+ "w": 25,
29
+ "x": 26,
30
+ "y": 27,
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
  }