anzorq commited on
Commit
3f5c2d2
1 Parent(s): f310d0d

Upload 4 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 49,
3
+ "<s>": 48
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "46": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "47": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "48": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "49": {
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
+ "processor_class": "Wav2Vec2BertProcessor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "[UNK]",
47
+ "word_delimiter_token": "|"
48
+ }
vocab.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "(": 1,
3
+ ")": 2,
4
+ "1": 3,
5
+ "2": 4,
6
+ "3": 5,
7
+ "4": 6,
8
+ "6": 7,
9
+ "9": 8,
10
+ "[PAD]": 47,
11
+ "[UNK]": 46,
12
+ "|": 0,
13
+ "а": 9,
14
+ "б": 10,
15
+ "в": 11,
16
+ "г": 12,
17
+ "д": 13,
18
+ "е": 14,
19
+ "ж": 15,
20
+ "з": 16,
21
+ "и": 17,
22
+ "й": 18,
23
+ "к": 19,
24
+ "л": 20,
25
+ "м": 21,
26
+ "н": 22,
27
+ "о": 23,
28
+ "п": 24,
29
+ "р": 25,
30
+ "с": 26,
31
+ "т": 27,
32
+ "у": 28,
33
+ "ф": 29,
34
+ "х": 30,
35
+ "ц": 31,
36
+ "ч": 32,
37
+ "ш": 33,
38
+ "щ": 34,
39
+ "ъ": 35,
40
+ "ы": 36,
41
+ "ь": 37,
42
+ "э": 38,
43
+ "ю": 39,
44
+ "я": 40,
45
+ "ё": 41,
46
+ "ӏ": 42,
47
+ "–": 43,
48
+ "—": 44,
49
+ "…": 45
50
+ }