AidenWilliams commited on
Commit
242bcb2
1 Parent(s): 659a008

Upload 5 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 47,
3
+ "<s>": 46
4
+ }
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "44": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "45": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "46": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "47": {
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 @@
 
 
1
+ {"g": 0, "k": 1, "\u00ec": 2, "w": 3, "d": 4, "p": 5, "\u00f3": 6, "o": 7, "n": 8, "\u0127": 9, "x": 10, "\u0121": 11, "\u00f9": 12, "b": 13, "f": 14, "\u00e9": 15, "j": 16, "4": 17, "a": 18, "m": 19, "e": 20, "\u0107": 21, "\u017c": 22, "q": 23, "s": 24, "y": 25, "\u010b": 26, "\u00ed": 27, "-": 28, "t": 29, "h": 30, "r": 31, "i": 32, "\u00e1": 33, "u": 34, "v": 35, "c": 37, "\u00f2": 38, "`": 39, "l": 40, "\u00e0": 41, "\u00e8": 42, "z": 43, "|": 36, "[UNK]": 44, "[PAD]": 45}