Hugging Face's logo

Lasion
/
wav2vec2-common-voice-17_0_vi

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Lasion commited on
Commit
3fe392e
•
1 Parent(s): 2aa77e2

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +23 -1
  2. tokenizer_config.json +11 -7
  3. vocab.json +1 -1
special_tokens_map.json CHANGED
@@ -1,6 +1,28 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
3
- "eos_token": "</s>",
 
 
 
 
 
 
4
  "pad_token": "<pad>",
5
  "unk_token": "<unk>"
6
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
  "bos_token": "<s>",
19
+ "eos_token": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
  "pad_token": "<pad>",
27
  "unk_token": "<unk>"
28
  }
tokenizer_config.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
  "added_tokens_decoder": {
3
- "0": {
4
- "content": "<pad>",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
8
  "single_word": false,
9
  "special": false
10
  },
11
- "94": {
12
- "content": "<unk>",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
@@ -27,22 +27,26 @@
27
  "97": {
28
  "content": "</s>",
29
  "lstrip": false,
30
- "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  }
35
  },
 
 
 
 
36
  "bos_token": "<s>",
37
  "clean_up_tokenization_spaces": true,
38
  "do_lower_case": 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",
45
- "tokenizer_file": "/content/wav2vec2-base-vi/tokenizer_config.json",
46
  "unk_token": "<unk>",
47
  "word_delimiter_token": "|"
48
  }
 
1
  {
2
  "added_tokens_decoder": {
3
+ "94": {
4
+ "content": "<unk>",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "95": {
12
+ "content": "<pad>",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
 
27
  "97": {
28
  "content": "</s>",
29
  "lstrip": false,
30
+ "normalized": true,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  }
35
  },
36
+ "additional_special_tokens": [
37
+ "<s>",
38
+ "</s>"
39
+ ],
40
  "bos_token": "<s>",
41
  "clean_up_tokenization_spaces": true,
42
  "do_lower_case": false,
43
+ "eos_token": "<s>",
44
  "model_max_length": 1000000000000000019884624838656,
45
  "pad_token": "<pad>",
46
+ "processor_class": "Wav2Vec2Processor",
47
  "replace_word_delimiter_char": " ",
48
  "target_lang": null,
49
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
50
  "unk_token": "<unk>",
51
  "word_delimiter_token": "|"
52
  }
vocab.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "<pad>": 0,
3
  "<unk>": 94,
4
  "a": 1,
5
  "b": 2,
 
1
  {
2
+ "<pad>": 95,
3
  "<unk>": 94,
4
  "a": 1,
5
  "b": 2,