Sagicc commited on
Commit
278b6c6
1 Parent(s): 0602e0c

Upload processor

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 +33 -32
README.md CHANGED
@@ -1,18 +1,18 @@
1
  ---
2
  license: mit
3
- base_model: facebook/w2v-bert-2.0
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
  - common_voice_16_1
8
  metrics:
9
  - wer
 
10
  model-index:
11
  - name: w2v-bert-2.0-sr
12
  results:
13
  - task:
14
- name: Automatic Speech Recognition
15
  type: automatic-speech-recognition
 
16
  dataset:
17
  name: common_voice_16_1
18
  type: common_voice_16_1
@@ -20,9 +20,9 @@ model-index:
20
  split: test
21
  args: sr
22
  metrics:
23
- - name: Wer
24
- type: wer
25
  value: 0.06932439583700829
 
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_trainer
5
  datasets:
6
  - common_voice_16_1
7
  metrics:
8
  - wer
9
+ base_model: facebook/w2v-bert-2.0
10
  model-index:
11
  - name: w2v-bert-2.0-sr
12
  results:
13
  - task:
 
14
  type: automatic-speech-recognition
15
+ name: Automatic Speech Recognition
16
  dataset:
17
  name: common_voice_16_1
18
  type: common_voice_16_1
 
20
  split: test
21
  args: sr
22
  metrics:
23
+ - type: wer
 
24
  value: 0.06932439583700829
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>": 34,
3
- "<s>": 33
4
  }
 
1
  {
2
+ "</s>": 35,
3
+ "<s>": 34
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "31": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "32": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "33": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "34": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "32": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "33": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "34": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "35": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,35 +1,36 @@
1
  {
2
- "[PAD]": 32,
3
- "[UNK]": 31,
4
  "|": 0,
5
- "а": 1,
6
- "б": 2,
7
- "в": 3,
8
- "г": 4,
9
- "д": 5,
10
- "е": 6,
11
- "ж": 7,
12
- "з": 8,
13
- "и": 9,
14
- "к": 10,
15
- "л": 11,
16
- "м": 12,
17
- "н": 13,
18
- "о": 14,
19
- "п": 15,
20
- "р": 16,
21
- "с": 17,
22
- "т": 18,
23
- "у": 19,
24
- "ф": 20,
25
- "х": 21,
26
- "ц": 22,
27
- "ч": 23,
28
- "ш": 24,
29
- "ђ": 25,
30
- "ј": 26,
31
- "љ": 27,
32
- "њ": 28,
33
- "ћ": 29,
34
- "џ": 30
 
35
  }
 
1
  {
2
+ "[PAD]": 33,
3
+ "[UNK]": 32,
4
  "|": 0,
5
+ "đ": 1,
6
+ "а": 2,
7
+ "б": 3,
8
+ "в": 4,
9
+ "г": 5,
10
+ "д": 6,
11
+ "е": 7,
12
+ "ж": 8,
13
+ "з": 9,
14
+ "и": 10,
15
+ "к": 11,
16
+ "л": 12,
17
+ "м": 13,
18
+ "н": 14,
19
+ "о": 15,
20
+ "п": 16,
21
+ "р": 17,
22
+ "с": 18,
23
+ "т": 19,
24
+ "у": 20,
25
+ "ф": 21,
26
+ "х": 22,
27
+ "ц": 23,
28
+ "ч": 24,
29
+ "ш": 25,
30
+ "ђ": 26,
31
+ "ј": 27,
32
+ "љ": 28,
33
+ "њ": 29,
34
+ "ћ": 30,
35
+ "џ": 31
36
  }