Hugging Face's logo

khederwaaOne
/
wav2vec2-large-xls-r-300m-tr-somali

Transformers
Inference Endpoints
Model card Files Community
khederwaaOne commited on
Commit
e072954
•
1 Parent(s): 0f0832e

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 +44 -44
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
- {
2
- "</s>": 43,
3
- "<s>": 42
4
- }
 
1
+ {
2
+ "</s>": 43,
3
+ "<s>": 42
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
- "40": {
4
- "content": "[UNK]",
5
- "lstrip": true,
6
- "normalized": false,
7
- "rstrip": true,
8
- "single_word": false,
9
- "special": false
10
- },
11
- "41": {
12
- "content": "[PAD]",
13
- "lstrip": true,
14
- "normalized": false,
15
- "rstrip": true,
16
- "single_word": false,
17
- "special": false
18
- },
19
- "42": {
20
- "content": "<s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "43": {
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
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "40": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "41": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "42": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "43": {
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
@@ -1,44 +1,44 @@
1
- {
2
- "$": 1,
3
- "0": 2,
4
- "1": 3,
5
- "2": 4,
6
- "3": 5,
7
- "4": 6,
8
- "5": 7,
9
- "6": 8,
10
- "7": 9,
11
- "8": 10,
12
- "9": 11,
13
- "[PAD]": 41,
14
- "[UNK]": 40,
15
- "_": 12,
16
- "a": 13,
17
- "b": 14,
18
- "c": 15,
19
- "d": 16,
20
- "e": 17,
21
- "f": 18,
22
- "g": 19,
23
- "h": 20,
24
- "i": 21,
25
- "j": 22,
26
- "k": 23,
27
- "l": 24,
28
- "m": 25,
29
- "n": 26,
30
- "o": 27,
31
- "p": 28,
32
- "q": 29,
33
- "r": 30,
34
- "s": 31,
35
- "t": 32,
36
- "u": 33,
37
- "v": 34,
38
- "w": 35,
39
- "x": 36,
40
- "y": 37,
41
- "z": 38,
42
- "|": 0,
43
- "’": 39
44
- }
 
1
+ {
2
+ "$": 1,
3
+ "0": 2,
4
+ "1": 3,
5
+ "2": 4,
6
+ "3": 5,
7
+ "4": 6,
8
+ "5": 7,
9
+ "6": 8,
10
+ "7": 9,
11
+ "8": 10,
12
+ "9": 11,
13
+ "[PAD]": 41,
14
+ "[UNK]": 40,
15
+ "_": 12,
16
+ "a": 13,
17
+ "b": 14,
18
+ "c": 15,
19
+ "d": 16,
20
+ "e": 17,
21
+ "f": 18,
22
+ "g": 19,
23
+ "h": 20,
24
+ "i": 21,
25
+ "j": 22,
26
+ "k": 23,
27
+ "l": 24,
28
+ "m": 25,
29
+ "n": 26,
30
+ "o": 27,
31
+ "p": 28,
32
+ "q": 29,
33
+ "r": 30,
34
+ "s": 31,
35
+ "t": 32,
36
+ "u": 33,
37
+ "v": 34,
38
+ "w": 35,
39
+ "x": 36,
40
+ "y": 37,
41
+ "z": 38,
42
+ "|": 0,
43
+ "’": 39
44
+ }