Hugging Face's logo

lucas-meyer
/
seq-xls-r-fleurs_zu-run3-asr_xh-run4

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
lucas-meyer commited on
Commit
f8ed9c4
•
1 Parent(s): ad7067c

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +4 -0
  2. tokenizer_config.json +12 -0
  3. vocab.json +56 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "[PAD]",
3
+ "unk_token": "[UNK]"
4
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": null,
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": null,
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "$": 1,
3
+ "*": 2,
4
+ "+": 3,
5
+ "0": 4,
6
+ "1": 5,
7
+ "2": 6,
8
+ "3": 7,
9
+ "4": 8,
10
+ "5": 9,
11
+ "6": 10,
12
+ "7": 11,
13
+ "8": 12,
14
+ "9": 13,
15
+ "[PAD]": 53,
16
+ "[UNK]": 52,
17
+ "a": 14,
18
+ "b": 15,
19
+ "c": 16,
20
+ "d": 17,
21
+ "e": 18,
22
+ "f": 19,
23
+ "g": 20,
24
+ "h": 21,
25
+ "i": 22,
26
+ "j": 23,
27
+ "k": 24,
28
+ "l": 25,
29
+ "m": 26,
30
+ "n": 27,
31
+ "o": 28,
32
+ "p": 29,
33
+ "q": 30,
34
+ "r": 31,
35
+ "s": 32,
36
+ "t": 33,
37
+ "u": 34,
38
+ "v": 35,
39
+ "w": 36,
40
+ "x": 37,
41
+ "y": 38,
42
+ "z": 39,
43
+ "|": 0,
44
+ " ": 40,
45
+ "£": 41,
46
+ "¥": 42,
47
+ "ã": 43,
48
+ "é": 44,
49
+ "í": 45,
50
+ "ó": 46,
51
+ "ü": 47,
52
+ "ă": 48,
53
+ "ć": 49,
54
+ "ş": 50,
55
+ "": 51
56
+ }