Hugging Face's logo

Hunzla
/
voice_bot_wav2vec2

Model card Files Community
Hunzla commited on
Commit
36a61b5
•
1 Parent(s): cddf748

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +65 -0
  4. vocab.json +34 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "[PAD]": 33,
3
+ "[UNK]": 32
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "32": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "33": {
44
+ "content": "[PAD]",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": true,
54
+ "do_lower_case": false,
55
+ "do_normalize": true,
56
+ "eos_token": "</s>",
57
+ "model_max_length": 9223372036854775807,
58
+ "pad_token": "[PAD]",
59
+ "replace_word_delimiter_char": " ",
60
+ "return_attention_mask": false,
61
+ "target_lang": null,
62
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
63
+ "unk_token": "[UNK]",
64
+ "word_delimiter_token": "|"
65
+ }
vocab.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 27,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "A": 7,
8
+ "B": 24,
9
+ "C": 19,
10
+ "D": 14,
11
+ "E": 5,
12
+ "F": 20,
13
+ "G": 21,
14
+ "H": 11,
15
+ "I": 10,
16
+ "J": 29,
17
+ "K": 26,
18
+ "L": 15,
19
+ "M": 17,
20
+ "N": 9,
21
+ "O": 8,
22
+ "P": 23,
23
+ "Q": 30,
24
+ "R": 13,
25
+ "S": 12,
26
+ "T": 6,
27
+ "U": 16,
28
+ "V": 25,
29
+ "W": 18,
30
+ "X": 28,
31
+ "Y": 22,
32
+ "Z": 31,
33
+ "|": 4
34
+ }