Hugging Face's logo

Kavin1701
/
wav2vec2-large-xls-r-300m-tamil2-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Kavin1701 commited on
Commit
d7bb6cb
·
verified ·
1 Parent(s): 0775c5e

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 +51 -57
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: apache-2.0
3
  base_model: Amrrs/wav2vec2-large-xlsr-53-tamil
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
1
  ---
 
2
  base_model: Amrrs/wav2vec2-large-xlsr-53-tamil
3
+ license: apache-2.0
4
  tags:
5
  - generated_from_trainer
6
  model-index:
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 59,
3
- "<s>": 58
4
  }
 
1
  {
2
+ "</s>": 53,
3
+ "<s>": 52
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "added_tokens_decoder": {
3
- "56": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "57": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "58": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "59": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
 
1
  {
2
  "added_tokens_decoder": {
3
+ "50": {
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
 
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "51": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "52": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "53": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
vocab.json CHANGED
@@ -1,60 +1,54 @@
1
  {
2
- "S": 1,
3
- "T": 2,
4
- "[PAD]": 57,
5
- "[UNK]": 56,
6
- "a": 3,
7
- "g": 4,
8
- "i": 5,
9
- "n": 6,
10
- "o": 7,
11
- "t": 8,
12
- "|": 0,
13
- "ஃ": 9,
14
- "அ": 10,
15
- "ஆ": 11,
16
- "இ": 12,
17
- "ஈ": 13,
18
- "உ": 14,
19
- "ஊ": 15,
20
- "எ": 16,
21
- "ஏ": 17,
22
- "ஐ": 18,
23
- "ஒ": 19,
24
- "ஓ": 20,
25
- "க": 21,
26
  "ங": 22,
27
- "ச": 23,
28
- "ஜ": 24,
29
- "ஞ": 25,
30
- "ட": 26,
31
- "ண": 27,
32
- "த": 28,
33
- "ந": 29,
34
- "ன": 30,
35
- "ப": 31,
36
- "ம": 32,
37
- "ய": 33,
38
- "ர": 34,
39
- "ற": 35,
40
- "ல": 36,
41
- "ள": 37,
42
- "ழ": 38,
43
- "வ": 39,
44
- "ஷ": 40,
45
- "ஸ": 41,
46
- "ஹ": 42,
47
- "ா": 43,
48
- "ி": 44,
49
- "ீ": 45,
50
- "ு": 46,
51
- "ூ": 47,
52
- "ெ": 48,
53
- "ே": 49,
54
- "ை": 50,
55
- "ொ": 51,
56
- "ோ": 52,
57
- "ௌ": 53,
58
- "்": 54,
59
- "’": 55
60
  }
 
1
  {
2
+ "'": 31,
3
+ "[PAD]": 51,
4
+ "[UNK]": 50,
5
+ "|": 13,
6
+ "ஃ": 39,
7
+ "அ": 32,
8
+ "ஆ": 38,
9
+ "இ": 34,
10
+ "ஈ": 2,
11
+ "உ": 44,
12
+ "ஊ": 18,
13
+ "எ": 23,
14
+ "ஏ": 9,
15
+ "ஐ": 47,
16
+ "ஒ": 33,
17
+ "ஓ": 7,
18
+ "ஔ": 19,
19
+ "க": 4,
 
 
 
 
 
 
20
  "ங": 22,
21
+ "ச": 29,
22
+ "ஜ": 10,
23
+ "ஞ": 42,
24
+ "ட": 8,
25
+ "ண": 41,
26
+ "த": 26,
27
+ "ந": 0,
28
+ "ன": 40,
29
+ "ப": 5,
30
+ "ம": 14,
31
+ "ய": 16,
32
+ "ர": 43,
33
+ "ற": 27,
34
+ "ல": 25,
35
+ "ள": 48,
36
+ "ழ": 49,
37
+ "வ": 35,
38
+ "ஷ": 6,
39
+ "ஸ": 20,
40
+ "ஹ": 12,
41
+ "ா": 1,
42
+ "ி": 3,
43
+ "ீ": 17,
44
+ "ு": 30,
45
+ "ூ": 28,
46
+ "ெ": 46,
47
+ "ே": 21,
48
+ "ை": 36,
49
+ "ொ": 11,
50
+ "ோ": 37,
51
+ "ௌ": 45,
52
+ "்": 24,
53
+ "’": 15
54
  }