bartelds commited on
Commit
b45a848
1 Parent(s): 2411cd4

Upload processor

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": 0.0,
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "/nvme/martijn/fine-tuning/nasal/cp0_adp0_168m-silver_24-orig/wav2vec2-xls-r-300m-1e-4",
6
+ "pad_token": "<pad>",
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "replace_word_delimiter_char": " ",
9
+ "special_tokens_map_file": "/nvme/martijn/fine-tuning/nasal/cp0_adp0_168m-silver_24-orig/wav2vec2-xls-r-300m-1e-4/special_tokens_map.json",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "<unk>",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 27,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "a": 7,
8
+ "b": 24,
9
+ "c": 19,
10
+ "d": 14,
11
+ "e": 5,
12
+ "f": 20,
13
+ "g": 21,
14
+ "h": 11,
15
+ "i": 10,
16
+ "j": 29,
17
+ "k": 26,
18
+ "l": 15,
19
+ "m": 17,
20
+ "n": 9,
21
+ "o": 8,
22
+ "p": 23,
23
+ "q": 30,
24
+ "r": 13,
25
+ "s": 12,
26
+ "t": 6,
27
+ "u": 16,
28
+ "v": 25,
29
+ "w": 18,
30
+ "x": 28,
31
+ "y": 22,
32
+ "z": 31,
33
+ "|": 4
34
+ }