Hugging Face's logo

jackmildice
/
w2v-bert-2.0-mongolian-colab-CV16.0

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2-bert
Inference Endpoints
Model card Files Community
jackmildice commited on
Commit
398170c
•
1 Parent(s): 075cf70

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 -48
  4. vocab.json +39 -39
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
- {
2
- "</s>": 38,
3
- "<s>": 37
4
- }
 
1
+ {
2
+ "</s>": 38,
3
+ "<s>": 37
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
@@ -1,48 +1,47 @@
1
- {
2
- "added_tokens_decoder": {
3
- "35": {
4
- "content": "[UNK]",
5
- "lstrip": true,
6
- "normalized": false,
7
- "rstrip": true,
8
- "single_word": false,
9
- "special": false
10
- },
11
- "36": {
12
- "content": "[PAD]",
13
- "lstrip": true,
14
- "normalized": false,
15
- "rstrip": true,
16
- "single_word": false,
17
- "special": false
18
- },
19
- "37": {
20
- "content": "<s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "38": {
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
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "35": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "36": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "37": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "38": {
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
@@ -1,39 +1,39 @@
1
- {
2
- "[PAD]": 36,
3
- "[UNK]": 35,
4
- "|": 0,
5
- "а": 1,
6
- "б": 2,
7
- "в": 3,
8
- "г": 4,
9
- "д": 5,
10
- "е": 6,
11
- "ж": 7,
12
- "з": 8,
13
- "и": 9,
14
- "й": 10,
15
- "к": 11,
16
- "л": 12,
17
- "м": 13,
18
- "н": 14,
19
- "о": 15,
20
- "п": 16,
21
- "р": 17,
22
- "с": 18,
23
- "т": 19,
24
- "у": 20,
25
- "ф": 21,
26
- "х": 22,
27
- "ц": 23,
28
- "ч": 24,
29
- "ш": 25,
30
- "ъ": 26,
31
- "ы": 27,
32
- "ь": 28,
33
- "э": 29,
34
- "ю": 30,
35
- "я": 31,
36
- "ё": 32,
37
- "ү": 33,
38
- "ө": 34
39
- }
 
1
+ {
2
+ "[PAD]": 36,
3
+ "[UNK]": 35,
4
+ "|": 0,
5
+ "а": 1,
6
+ "б": 2,
7
+ "в": 3,
8
+ "г": 4,
9
+ "д": 5,
10
+ "е": 6,
11
+ "ж": 7,
12
+ "з": 8,
13
+ "и": 9,
14
+ "й": 10,
15
+ "к": 11,
16
+ "л": 12,
17
+ "м": 13,
18
+ "н": 14,
19
+ "о": 15,
20
+ "п": 16,
21
+ "р": 17,
22
+ "с": 18,
23
+ "т": 19,
24
+ "у": 20,
25
+ "ф": 21,
26
+ "х": 22,
27
+ "ц": 23,
28
+ "ч": 24,
29
+ "ш": 25,
30
+ "ъ": 26,
31
+ "ы": 27,
32
+ "ь": 28,
33
+ "э": 29,
34
+ "ю": 30,
35
+ "я": 31,
36
+ "ё": 32,
37
+ "ү": 33,
38
+ "ө": 34
39
+ }