Hugging Face's logo

EzraWilliam
/
wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
EzraWilliam commited on
Commit
1515ea9
·
verified ·
1 Parent(s): debb90a

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. added_tokens.json +2 -2
  3. tokenizer_config.json +4 -4
  4. vocab.json +62 -30
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
  license: apache-2.0
3
- base_model: facebook/wav2vec2-xls-r-300m
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
  - wer
 
8
  model-index:
9
  - name: wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
10
  results: []
 
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
6
  - wer
7
+ base_model: facebook/wav2vec2-xls-r-300m
8
  model-index:
9
  - name: wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
10
  results: []
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 32,
3
- "<s>": 31
4
  }
 
1
  {
2
+ "</s>": 64,
3
+ "<s>": 63
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "29": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "30": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "31": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "32": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "61": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "62": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "63": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "64": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,33 +1,65 @@
1
  {
2
- "\"": 12,
3
- "'": 5,
4
- "[PAD]": 30,
5
- "[UNK]": 29,
6
- "a": 26,
7
- "b": 3,
8
- "c": 2,
9
- "d": 13,
10
- "e": 15,
11
- "f": 6,
12
- "g": 4,
13
- "h": 19,
14
- "i": 22,
15
- "j": 0,
 
 
 
 
 
 
 
 
 
 
 
 
16
  "k": 25,
17
- "l": 11,
18
- "m": 17,
19
- "n": 21,
20
- "o": 8,
21
- "p": 16,
22
- "q": 1,
23
- "r": 24,
24
- "s": 27,
25
- "t": 14,
26
- "u": 23,
27
- "v": 28,
28
- "w": 18,
29
- "x": 7,
30
- "y": 20,
31
- "z": 10,
32
- "|": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
 
1
  {
2
+ "$": 1,
3
+ "&": 2,
4
+ "+": 3,
5
+ "/": 4,
6
+ "0": 5,
7
+ "1": 6,
8
+ "2": 7,
9
+ "3": 8,
10
+ "4": 9,
11
+ "5": 10,
12
+ "6": 11,
13
+ "7": 12,
14
+ "8": 13,
15
+ "9": 14,
16
+ "[PAD]": 62,
17
+ "[UNK]": 61,
18
+ "a": 15,
19
+ "b": 16,
20
+ "c": 17,
21
+ "d": 18,
22
+ "e": 19,
23
+ "f": 20,
24
+ "g": 21,
25
+ "h": 22,
26
+ "i": 23,
27
+ "j": 24,
28
  "k": 25,
29
+ "l": 26,
30
+ "m": 27,
31
+ "n": 28,
32
+ "o": 29,
33
+ "p": 30,
34
+ "q": 31,
35
+ "r": 32,
36
+ "s": 33,
37
+ "t": 34,
38
+ "u": 35,
39
+ "v": 36,
40
+ "w": 37,
41
+ "x": 38,
42
+ "y": 39,
43
+ "z": 40,
44
+ "|": 0,
45
+ "¡": 41,
46
+ "£": 42,
47
+ "¥": 43,
48
+ "§": 44,
49
+ "©": 45,
50
+ "­": 46,
51
+ "°": 47,
52
+ "±": 48,
53
+ "²": 49,
54
+ "³": 50,
55
+ "µ": 51,
56
+ "¶": 52,
57
+ "º": 53,
58
+ "ã": 54,
59
+ "ä": 55,
60
+ "å": 56,
61
+ "ÿ": 57,
62
+ "ƒ": 58,
63
+ "•": 59,
64
+ "€": 60
65
  }