Ar4ikov commited on
Commit
c4960b9
1 Parent(s): 0a536bf

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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "Ar4ikov/wav2vec2-projector-russian-resd",
7
+ "pad_token": "<pad>",
8
+ "processor_class": "Wav2Vec2Processor",
9
+ "replace_word_delimiter_char": " ",
10
+ "special_tokens_map_file": "/home/ar4ikov/.cache/huggingface/hub/models--jonatasgrosman--wav2vec2-large-xlsr-53-russian/snapshots/2329100508896c6d9b157019803ab5601e6f3406/special_tokens_map.json",
11
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
12
+ "unk_token": "<unk>",
13
+ "word_delimiter_token": "|"
14
+ }
vocab.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "-": 5,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "|": 4,
8
+ "а": 7,
9
+ "б": 8,
10
+ "в": 9,
11
+ "г": 10,
12
+ "д": 11,
13
+ "е": 12,
14
+ "ж": 13,
15
+ "з": 14,
16
+ "и": 15,
17
+ "й": 16,
18
+ "к": 17,
19
+ "л": 18,
20
+ "м": 19,
21
+ "н": 20,
22
+ "о": 21,
23
+ "п": 22,
24
+ "р": 23,
25
+ "с": 24,
26
+ "т": 25,
27
+ "у": 26,
28
+ "ф": 27,
29
+ "х": 28,
30
+ "ц": 29,
31
+ "ч": 30,
32
+ "ш": 31,
33
+ "щ": 32,
34
+ "ъ": 33,
35
+ "ы": 34,
36
+ "ь": 35,
37
+ "э": 36,
38
+ "ю": 37,
39
+ "я": 38,
40
+ "ё": 6
41
+ }