Hugging Face's logo

Roxysun
/
wav2vec2-large-xls-r-300m-hungarian-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Roxysun commited on
Commit
c60b1e8
·
1 Parent(s): cd08916

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +37 -38
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 42,
3
- "<s>": 41
4
  }
 
1
  {
2
+ "</s>": 41,
3
+ "<s>": 40
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "39": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "40": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "41": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": true,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "42": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
 
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": true,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "41": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
vocab.json CHANGED
@@ -1,43 +1,42 @@
1
  {
2
  "!": 1,
3
  ".": 2,
4
- ";": 3,
5
- "?": 4,
6
- "[PAD]": 40,
7
- "[UNK]": 39,
8
- "a": 5,
9
- "b": 6,
10
- "c": 7,
11
- "d": 8,
12
- "e": 9,
13
- "f": 10,
14
- "g": 11,
15
- "h": 12,
16
- "i": 13,
17
- "j": 14,
18
- "k": 15,
19
- "l": 16,
20
- "m": 17,
21
- "n": 18,
22
- "o": 19,
23
- "p": 20,
24
- "q": 21,
25
- "r": 22,
26
- "s": 23,
27
- "t": 24,
28
- "u": 25,
29
- "v": 26,
30
- "w": 27,
31
- "x": 28,
32
- "y": 29,
33
- "z": 30,
34
  "|": 0,
35
- "á": 31,
36
- "é": 32,
37
- "ó": 33,
38
- "ö": 34,
39
- "ú": 35,
40
- "ü": 36,
41
- "ő": 37,
42
- "ű": 38
43
  }
 
1
  {
2
  "!": 1,
3
  ".": 2,
4
+ "?": 3,
5
+ "[PAD]": 39,
6
+ "[UNK]": 38,
7
+ "a": 4,
8
+ "b": 5,
9
+ "c": 6,
10
+ "d": 7,
11
+ "e": 8,
12
+ "f": 9,
13
+ "g": 10,
14
+ "h": 11,
15
+ "i": 12,
16
+ "j": 13,
17
+ "k": 14,
18
+ "l": 15,
19
+ "m": 16,
20
+ "n": 17,
21
+ "o": 18,
22
+ "p": 19,
23
+ "q": 20,
24
+ "r": 21,
25
+ "s": 22,
26
+ "t": 23,
27
+ "u": 24,
28
+ "v": 25,
29
+ "w": 26,
30
+ "x": 27,
31
+ "y": 28,
32
+ "z": 29,
 
33
  "|": 0,
34
+ "á": 30,
35
+ "é": 31,
36
+ "ó": 32,
37
+ "ö": 33,
38
+ "ú": 34,
39
+ "ü": 35,
40
+ "ő": 36,
41
+ "ű": 37
42
  }