TifinLab commited on
Commit
a22b0bd
1 Parent(s): 3db47ff

Upload processor

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. added_tokens.json +4 -0
  3. special_tokens_map.json +30 -0
  4. tokenizer_config.json +48 -0
  5. vocab.json +55 -0
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- library_name: transformers
3
  base_model: TifinLab/xlsr-kab
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
1
  ---
 
2
  base_model: TifinLab/xlsr-kab
3
+ library_name: transformers
4
  tags:
5
  - generated_from_trainer
6
  model-index:
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 54,
3
+ "<s>": 53
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "51": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "52": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "53": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "54": {
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": "Wav2Vec2Processor",
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "-": 1,
3
+ "0": 2,
4
+ "1": 3,
5
+ "2": 4,
6
+ "3": 5,
7
+ "5": 6,
8
+ "6": 7,
9
+ "7": 8,
10
+ "8": 9,
11
+ "9": 10,
12
+ "[PAD]": 52,
13
+ "[UNK]": 51,
14
+ "a": 11,
15
+ "b": 12,
16
+ "c": 13,
17
+ "d": 14,
18
+ "e": 15,
19
+ "f": 16,
20
+ "g": 17,
21
+ "h": 18,
22
+ "i": 19,
23
+ "j": 20,
24
+ "k": 21,
25
+ "l": 22,
26
+ "m": 23,
27
+ "n": 24,
28
+ "o": 25,
29
+ "p": 26,
30
+ "q": 27,
31
+ "r": 28,
32
+ "s": 29,
33
+ "t": 30,
34
+ "u": 31,
35
+ "v": 32,
36
+ "w": 33,
37
+ "x": 34,
38
+ "y": 35,
39
+ "z": 36,
40
+ "|": 0,
41
+ "ç": 37,
42
+ "č": 38,
43
+ "ǧ": 39,
44
+ "ɛ": 40,
45
+ "ɣ": 41,
46
+ "̣": 42,
47
+ "σ": 43,
48
+ "ḍ": 44,
49
+ "ḥ": 45,
50
+ "ṛ": 46,
51
+ "ṣ": 47,
52
+ "ṭ": 48,
53
+ "ẓ": 49,
54
+ "€": 50
55
+ }