SaiPatil commited on
Commit
cc6afd4
1 Parent(s): 86d1d5e

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +47 -0
  4. vocab.json +34 -0
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
3
- base_model: facebook/wav2vec2-base-960h
4
  tags:
5
  - generated_from_keras_callback
 
6
  model-index:
7
  - name: wav2vec
8
  results: []
 
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_keras_callback
5
+ base_model: facebook/wav2vec2-base-960h
6
  model-index:
7
  - name: wav2vec
8
  results: []
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "do_normalize": true,
40
+ "eos_token": "</s>",
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<pad>",
43
+ "return_attention_mask": false,
44
+ "tokenizer_class": "Wav2Vec2Tokenizer",
45
+ "unk_token": "<unk>",
46
+ "word_delimiter_token": "|"
47
+ }
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
+ }