Hugging Face's logo

digicazter
/
wav2vec2-base-timit-demo-google-colab

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
3
digicazter commited on
Commit
9a0d2eb
•
1 Parent(s): 6fae78b

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer_config.json +1 -1
  2. vocab.json +32 -39
tokenizer_config.json CHANGED
@@ -9,5 +9,5 @@
9
  "target_lang": null,
10
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
  "unk_token": "[UNK]",
12
- "word_delimiter_token": " "
13
  }
 
9
  "target_lang": null,
10
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
  "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
  }
vocab.json CHANGED
@@ -1,41 +1,34 @@
1
  {
2
- "'": 4,
3
- "0": 33,
4
- "1": 20,
5
- "2": 32,
6
- "3": 34,
7
- "5": 3,
8
- "6": 36,
9
- "7": 22,
10
- "8": 25,
11
- "9": 35,
12
- "[PAD]": 38,
13
- "[UNK]": 37,
14
- "a": 21,
15
- "b": 30,
16
- "c": 19,
17
- "d": 31,
18
- "e": 1,
19
- "f": 29,
20
- "g": 12,
21
- "h": 8,
22
- "i": 27,
23
- "j": 2,
24
- "k": 13,
25
- "l": 18,
26
- "m": 10,
27
- "n": 9,
28
- "o": 17,
29
- "p": 23,
30
- "q": 11,
31
- "r": 28,
32
- "s": 24,
33
- "t": 5,
34
- "u": 15,
35
- "v": 0,
36
- "w": 7,
37
- "x": 6,
38
- "y": 16,
39
- "z": 14,
40
- "|": 26
41
  }
 
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
  }