Hugging Face's logo

dmatekenya
/
wav2vec2-large-xls-r-300m-chichewa

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
dmatekenya commited on
Commit
2cd687d
·
1 Parent(s): 6624f86

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +13 -0
  3. vocab.json +49 -0
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "target_lang": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t": 0,
3
+ "$": 2,
4
+ "(": 3,
5
+ ")": 4,
6
+ "/": 5,
7
+ "0": 6,
8
+ "1": 7,
9
+ "2": 8,
10
+ "3": 9,
11
+ "4": 10,
12
+ "5": 11,
13
+ "6": 12,
14
+ "7": 13,
15
+ "8": 14,
16
+ "9": 15,
17
+ "[PAD]": 46,
18
+ "[UNK]": 45,
19
+ "a": 16,
20
+ "b": 17,
21
+ "c": 18,
22
+ "d": 19,
23
+ "e": 20,
24
+ "f": 21,
25
+ "g": 22,
26
+ "h": 23,
27
+ "i": 24,
28
+ "j": 25,
29
+ "k": 26,
30
+ "l": 27,
31
+ "m": 28,
32
+ "n": 29,
33
+ "o": 30,
34
+ "p": 31,
35
+ "q": 32,
36
+ "r": 33,
37
+ "s": 34,
38
+ "t": 35,
39
+ "u": 36,
40
+ "v": 37,
41
+ "w": 38,
42
+ "x": 39,
43
+ "y": 40,
44
+ "z": 41,
45
+ "|": 1,
46
+ "’": 42,
47
+ "…": 43,
48
+ "": 44
49
+ }