Hugging Face's logo

pinot
/
wav2vec2-xls-r-1b-ja-phoneme_cv_14_3

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
1
pinot commited on
Commit
d1c36d9
•
1 Parent(s): 6d6c010

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 +56 -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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<pad>": 0,
4
+ "<s>": 1,
5
+ "<unk>": 3,
6
+ "F": 5,
7
+ "N": 6,
8
+ "Q": 7,
9
+ "a": 8,
10
+ "aH": 9,
11
+ "b": 10,
12
+ "by": 11,
13
+ "c": 12,
14
+ "cj": 13,
15
+ "cy": 14,
16
+ "d": 15,
17
+ "e": 16,
18
+ "eH": 17,
19
+ "g": 18,
20
+ "gj": 19,
21
+ "gw": 20,
22
+ "gy": 21,
23
+ "h": 22,
24
+ "hj": 23,
25
+ "hy": 24,
26
+ "i": 25,
27
+ "iH": 26,
28
+ "k": 27,
29
+ "kj": 28,
30
+ "kw": 29,
31
+ "ky": 30,
32
+ "m": 31,
33
+ "my": 32,
34
+ "n": 33,
35
+ "nj": 34,
36
+ "ny": 35,
37
+ "o": 36,
38
+ "oH": 37,
39
+ "p": 38,
40
+ "py": 39,
41
+ "r": 40,
42
+ "ry": 41,
43
+ "s": 42,
44
+ "sj": 43,
45
+ "sy": 44,
46
+ "t": 45,
47
+ "u": 46,
48
+ "uH": 47,
49
+ "v": 48,
50
+ "w": 49,
51
+ "y": 50,
52
+ "z": 51,
53
+ "zj": 52,
54
+ "zy": 53,
55
+ "|": 4
56
+ }