Maverick1713 commited on
Commit
bbe7504
·
verified ·
1 Parent(s): 2160a4f

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -4
  2. special_tokens_map.json +6 -6
  3. tokenizer_config.json +47 -47
  4. vocab.json +43 -43
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
- {
2
- "</s>": 42,
3
- "<s>": 41
4
- }
 
1
+ {
2
+ "</s>": 42,
3
+ "<s>": 41
4
+ }
special_tokens_map.json CHANGED
@@ -1,6 +1,6 @@
1
- {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "pad_token": "[PAD]",
5
- "unk_token": "[UNK]"
6
- }
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json CHANGED
@@ -1,47 +1,47 @@
1
- {
2
- "added_tokens_decoder": {
3
- "39": {
4
- "content": "[UNK]",
5
- "lstrip": true,
6
- "normalized": false,
7
- "rstrip": true,
8
- "single_word": false,
9
- "special": false
10
- },
11
- "40": {
12
- "content": "[PAD]",
13
- "lstrip": true,
14
- "normalized": false,
15
- "rstrip": true,
16
- "single_word": false,
17
- "special": false
18
- },
19
- "41": {
20
- "content": "<s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "42": {
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": false,
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
- "unk_token": "[UNK]",
46
- "word_delimiter_token": "|"
47
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "39": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "40": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "41": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "42": {
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
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json CHANGED
@@ -1,43 +1,43 @@
1
- {
2
- "$": 2,
3
- "'": 12,
4
- "0": 18,
5
- "1": 37,
6
- "2": 9,
7
- "3": 8,
8
- "4": 34,
9
- "5": 32,
10
- "6": 5,
11
- "7": 33,
12
- "8": 13,
13
- "9": 14,
14
- "[PAD]": 40,
15
- "[UNK]": 39,
16
- "a": 35,
17
- "b": 6,
18
- "c": 20,
19
- "d": 15,
20
- "e": 25,
21
- "f": 7,
22
- "g": 11,
23
- "h": 28,
24
- "i": 21,
25
- "j": 30,
26
- "k": 1,
27
- "l": 19,
28
- "m": 17,
29
- "n": 22,
30
- "o": 24,
31
- "p": 10,
32
- "q": 3,
33
- "r": 31,
34
- "s": 16,
35
- "t": 4,
36
- "u": 26,
37
- "v": 36,
38
- "w": 29,
39
- "x": 27,
40
- "y": 23,
41
- "z": 38,
42
- "|": 0
43
- }
 
1
+ {
2
+ "$": 31,
3
+ "'": 27,
4
+ "0": 26,
5
+ "1": 18,
6
+ "2": 37,
7
+ "3": 12,
8
+ "4": 35,
9
+ "5": 4,
10
+ "6": 14,
11
+ "7": 7,
12
+ "8": 32,
13
+ "9": 22,
14
+ "[PAD]": 40,
15
+ "[UNK]": 39,
16
+ "a": 33,
17
+ "b": 36,
18
+ "c": 25,
19
+ "d": 21,
20
+ "e": 0,
21
+ "f": 38,
22
+ "g": 2,
23
+ "h": 29,
24
+ "i": 9,
25
+ "j": 16,
26
+ "k": 15,
27
+ "l": 10,
28
+ "m": 3,
29
+ "n": 6,
30
+ "o": 11,
31
+ "p": 19,
32
+ "q": 8,
33
+ "r": 17,
34
+ "s": 1,
35
+ "t": 30,
36
+ "u": 20,
37
+ "v": 5,
38
+ "w": 24,
39
+ "x": 23,
40
+ "y": 28,
41
+ "z": 34,
42
+ "|": 13
43
+ }