Hugging Face's logo

cdactvm
/
w2v-bert-kannada_new

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Model card Files
xet
Metrics Community
cdactvm commited on
Commit
4681f8f
·
verified ·
1 Parent(s): a12ad7e

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -5
  3. vocab.json +5 -8
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 95,
3
- "<s>": 94
4
  }
 
1
  {
2
+ "</s>": 92,
3
+ "<s>": 91
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "92": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "93": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "94": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "95": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
@@ -39,7 +39,6 @@
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
42
- "processor_class": "Wav2Vec2BertProcessor",
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": null,
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
1
  {
2
  "added_tokens_decoder": {
3
+ "89": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "90": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "91": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "92": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
39
  "eos_token": "</s>",
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
 
42
  "replace_word_delimiter_char": " ",
43
  "target_lang": null,
44
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
vocab.json CHANGED
@@ -12,8 +12,8 @@
12
  "9": 11,
13
  "I": 12,
14
  "U": 13,
15
- "[PAD]": 93,
16
- "[UNK]": 92,
17
  "_": 14,
18
  "|": 0,
19
  "ಂ": 15,
@@ -87,10 +87,7 @@
87
  "೩": 83,
88
  "೪": 84,
89
  "೫": 85,
90
- "೬": 86,
91
- "೭": 87,
92
- "೮": 88,
93
- "೯": 89,
94
- "​": 90,
95
- "‍": 91
96
  }
 
12
  "9": 11,
13
  "I": 12,
14
  "U": 13,
15
+ "[PAD]": 90,
16
+ "[UNK]": 89,
17
  "_": 14,
18
  "|": 0,
19
  "ಂ": 15,
 
87
  "೩": 83,
88
  "೪": 84,
89
  "೫": 85,
90
+ "೮": 86,
91
+ "​": 87,
92
+ "‍": 88
 
 
 
93
  }