jimregan commited on
Commit
1924623
1 Parent(s): 92501fa

add model files

Browse files
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,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb404e64ed068bf62a22eb7251d45b2ab124f6950d26f48ab803347ea3f6ccb8
3
+ size 1262043565
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 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "<pad>",
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "replace_word_delimiter_char": " ",
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "<unk>",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "-": 4,
3
+ ":": 5,
4
+ "</s>": 2,
5
+ "<pad>": 0,
6
+ "<s>": 1,
7
+ "<unk>": 3,
8
+ "a": 6,
9
+ "b": 7,
10
+ "c": 8,
11
+ "d": 9,
12
+ "e": 10,
13
+ "f": 11,
14
+ "g": 12,
15
+ "h": 13,
16
+ "i": 14,
17
+ "j": 15,
18
+ "k": 16,
19
+ "l": 17,
20
+ "m": 18,
21
+ "n": 19,
22
+ "o": 20,
23
+ "p": 21,
24
+ "r": 22,
25
+ "s": 23,
26
+ "t": 24,
27
+ "u": 25,
28
+ "v": 26,
29
+ "w": 27,
30
+ "x": 28,
31
+ "y": 29,
32
+ "z": 30,
33
+ "|": 31,
34
+ "ä": 32,
35
+ "å": 33,
36
+ "é": 34,
37
+ "ö": 35
38
+ }