St4n commited on
Commit
d87614a
1 Parent(s): 3a53452

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +4 -4
  2. added_tokens.json +2 -2
  3. tokenizer_config.json +4 -4
  4. vocab.json +18 -19
README.md CHANGED
@@ -1,18 +1,18 @@
1
  ---
2
  license: apache-2.0
3
- base_model: facebook/wav2vec2-base-960h
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
  - fleurs
8
  metrics:
9
  - wer
 
10
  model-index:
11
  - name: wav2vec2-base-fleurs-329-colab-a100-2
12
  results:
13
  - task:
14
- name: Automatic Speech Recognition
15
  type: automatic-speech-recognition
 
16
  dataset:
17
  name: fleurs
18
  type: fleurs
@@ -20,9 +20,9 @@ model-index:
20
  split: test
21
  args: en_us
22
  metrics:
23
- - name: Wer
24
- type: wer
25
  value: 0.9917617237008872
 
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
  datasets:
6
  - fleurs
7
  metrics:
8
  - wer
9
+ base_model: facebook/wav2vec2-base-960h
10
  model-index:
11
  - name: wav2vec2-base-fleurs-329-colab-a100-2
12
  results:
13
  - task:
 
14
  type: automatic-speech-recognition
15
+ name: Automatic Speech Recognition
16
  dataset:
17
  name: fleurs
18
  type: fleurs
 
20
  split: test
21
  args: en_us
22
  metrics:
23
+ - type: wer
 
24
  value: 0.9917617237008872
25
+ name: Wer
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 30,
3
- "<s>": 29
4
  }
 
1
  {
2
+ "</s>": 29,
3
+ "<s>": 28
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "27": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "28": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "29": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "30": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "26": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "27": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "28": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "29": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "[PAD]": 28,
3
- "[UNK]": 27,
4
  "a": 1,
5
  "b": 2,
6
  "c": 3,
@@ -10,22 +10,21 @@
10
  "g": 7,
11
  "h": 8,
12
  "i": 9,
13
- "j": 10,
14
- "k": 11,
15
- "l": 12,
16
- "m": 13,
17
- "n": 14,
18
- "o": 15,
19
- "p": 16,
20
- "q": 17,
21
- "r": 18,
22
- "s": 19,
23
- "t": 20,
24
- "u": 21,
25
- "v": 22,
26
- "w": 23,
27
- "x": 24,
28
- "y": 25,
29
- "z": 26,
30
  "|": 0
31
  }
 
1
  {
2
+ "[PAD]": 27,
3
+ "[UNK]": 26,
4
  "a": 1,
5
  "b": 2,
6
  "c": 3,
 
10
  "g": 7,
11
  "h": 8,
12
  "i": 9,
13
+ "k": 10,
14
+ "l": 11,
15
+ "m": 12,
16
+ "n": 13,
17
+ "o": 14,
18
+ "p": 15,
19
+ "q": 16,
20
+ "r": 17,
21
+ "s": 18,
22
+ "t": 19,
23
+ "u": 20,
24
+ "v": 21,
25
+ "w": 22,
26
+ "x": 23,
27
+ "y": 24,
28
+ "z": 25,
 
29
  "|": 0
30
  }