snu-nia-12 commited on
Commit
29d7b42
1 Parent(s): 4513339
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 45,
3
+ "<s>": 44
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": false,
9
+ "sampling_rate": 16000
10
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "[PAD]",
21
+ "unk_token": "[UNK]"
22
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "speech31/wav2vec2-large-TIMIT-IPA",
6
+ "pad_token": "[PAD]",
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "replace_word_delimiter_char": " ",
9
+ "special_tokens_map_file": "/home/eunjung/.cache/huggingface/transformers/b31260877ff69a2d5d306ee8d1c8efbd7418f8355baafb3e14ba14e35026294b.fea372b8528a479b7415f13ca4e27a2f5f3782cbb3f15b4d19bb3cbe734e8137",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 16,
3
+ "[PAD]": 43,
4
+ "[UNK]": 42,
5
+ "a": 40,
6
+ "b": 30,
7
+ "c": 4,
8
+ "d": 2,
9
+ "e": 1,
10
+ "f": 27,
11
+ "g": 23,
12
+ "h": 26,
13
+ "i": 28,
14
+ "j": 0,
15
+ "k": 32,
16
+ "l": 3,
17
+ "m": 9,
18
+ "n": 24,
19
+ "o": 38,
20
+ "p": 29,
21
+ "q": 34,
22
+ "r": 11,
23
+ "s": 15,
24
+ "t": 35,
25
+ "u": 6,
26
+ "v": 41,
27
+ "w": 22,
28
+ "x": 37,
29
+ "y": 12,
30
+ "z": 13,
31
+ "|": 8,
32
+ "æ": 33,
33
+ "ð": 14,
34
+ "ŋ": 7,
35
+ "ɑ": 31,
36
+ "ɔ": 25,
37
+ "ə": 17,
38
+ "ɛ": 5,
39
+ "ɪ": 10,
40
+ "ʃ": 18,
41
+ "ʊ": 39,
42
+ "ʒ": 21,
43
+ "ʤ": 20,
44
+ "ʧ": 36,
45
+ "θ": 19
46
+ }