Hugging Face's logo

iammahadev
/
w2v-bert-2-malayalam-combo-v1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
iammahadev commited on
Commit
b34c9f4
•
1 Parent(s): d6f1fb2

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +3 -5
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 77,
3
- "<s>": 76
4
  }
 
1
  {
2
+ "</s>": 75,
3
+ "<s>": 74
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "74": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "75": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "76": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "77": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "72": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "73": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "74": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "75": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "[PAD]": 75,
3
- "[UNK]": 74,
4
  "|": 0,
5
  "ം": 1,
6
  "ഃ": 2,
@@ -72,7 +72,5 @@
72
  "ർ": 68,
73
  "ൽ": 69,
74
  "ൾ": 70,
75
- "ൿ": 71,
76
- "‌": 72,
77
- "‍": 73
78
  }
 
1
  {
2
+ "[PAD]": 73,
3
+ "[UNK]": 72,
4
  "|": 0,
5
  "ം": 1,
6
  "ഃ": 2,
 
72
  "ർ": 68,
73
  "ൽ": 69,
74
  "ൾ": 70,
75
+ "ൿ": 71
 
 
76
  }