Hugging Face's logo

sanjana-m
/
wav2vec2-large-xls-r-300m-gn-pt-colab

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
sanjana-m commited on
Commit
a78e938
•
1 Parent(s): a203017

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +4 -4
  3. vocab.json +8 -9
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 57,
3
- "<s>": 56
4
  }
 
1
  {
2
+ "</s>": 56,
3
+ "<s>": 55
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "54": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "55": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "56": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": true,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "57": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "53": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "54": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "55": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": true,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "56": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": true,
vocab.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "&": 1,
3
- "[PAD]": 55,
4
- "[UNK]": 54,
5
  "a": 2,
6
  "b": 3,
7
  "c": 4,
@@ -48,11 +48,10 @@
48
  "ý": 44,
49
  "ĩ": 45,
50
  "ũ": 46,
51
- "ž": 47,
52
- "ʼ": 48,
53
- "̃": 49,
54
- "ḡ": 50,
55
- "ẽ": 51,
56
- "ỹ": 52,
57
- "’": 53
58
  }
 
1
  {
2
  "&": 1,
3
+ "[PAD]": 54,
4
+ "[UNK]": 53,
5
  "a": 2,
6
  "b": 3,
7
  "c": 4,
 
48
  "ý": 44,
49
  "ĩ": 45,
50
  "ũ": 46,
51
+ "ʼ": 47,
52
+ "̃": 48,
53
+ "ḡ": 49,
54
+ "ẽ": 50,
55
+ "ỹ": 51,
56
+ "’": 52
 
57
  }