technotron commited on
Commit
cd38e69
·
verified ·
1 Parent(s): 5329bec

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 34,
3
+ "<s>": 33
4
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "32": {
20
+ "content": "[BLANK]",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "33": {
28
+ "content": "<s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "34": {
36
+ "content": "</s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "do_lower_case": false,
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "[PAD]",
51
+ "processor_class": "Wav2Vec2Processor",
52
+ "replace_word_delimiter_char": " ",
53
+ "target_lang": null,
54
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
55
+ "unk_token": "[UNK]",
56
+ "word_delimiter_token": "|"
57
+ }
vocab.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[BLANK]": 32,
3
+ "[PAD]": 0,
4
+ "[UNK]": 1,
5
+ "a": 3,
6
+ "b": 4,
7
+ "c": 5,
8
+ "d": 6,
9
+ "e": 7,
10
+ "f": 8,
11
+ "g": 9,
12
+ "h": 10,
13
+ "i": 11,
14
+ "j": 12,
15
+ "k": 13,
16
+ "l": 14,
17
+ "m": 15,
18
+ "n": 16,
19
+ "o": 17,
20
+ "p": 18,
21
+ "r": 19,
22
+ "s": 20,
23
+ "t": 21,
24
+ "u": 22,
25
+ "v": 23,
26
+ "w": 24,
27
+ "x": 25,
28
+ "y": 26,
29
+ "z": 27,
30
+ "|": 2,
31
+ "ŋ": 28,
32
+ "ɔ": 29,
33
+ "ɛ": 30,
34
+ "ɣ": 31
35
+ }