Hugging Face's logo

Kellner
/
mms-300m-turkish

Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
Kellner commited on
Commit
4b0e465
·
verified ·
1 Parent(s): 4099809

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +2 -2
  2. tokenizer_config.json +16 -16
  3. vocab.json +31 -28
special_tokens_map.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
- "pad_token": "[PAD]",
5
- "unk_token": "[UNK]"
6
  }
 
1
  {
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
  }
tokenizer_config.json CHANGED
@@ -1,36 +1,36 @@
1
  {
2
  "added_tokens_decoder": {
3
- "27": {
4
- "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
8
  "single_word": false,
9
  "special": false
10
  },
11
- "28": {
12
- "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
16
  "single_word": false,
17
  "special": false
18
  },
19
- "29": {
20
- "content": "<s>",
21
- "lstrip": false,
22
  "normalized": false,
23
- "rstrip": false,
24
  "single_word": false,
25
- "special": true
26
  },
27
- "30": {
28
- "content": "</s>",
29
- "lstrip": false,
30
  "normalized": false,
31
- "rstrip": false,
32
  "single_word": false,
33
- "special": true
34
  }
35
  },
36
  "bos_token": "<s>",
@@ -39,10 +39,10 @@
39
  "eos_token": "</s>",
40
  "extra_special_tokens": {},
41
  "model_max_length": 1000000000000000019884624838656,
42
- "pad_token": "[PAD]",
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": "tur",
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
- "unk_token": "[UNK]",
47
  "word_delimiter_token": "|"
48
  }
 
1
  {
2
  "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
  "lstrip": true,
6
  "normalized": false,
7
  "rstrip": true,
8
  "single_word": false,
9
  "special": false
10
  },
11
+ "1": {
12
+ "content": "<s>",
13
  "lstrip": true,
14
  "normalized": false,
15
  "rstrip": true,
16
  "single_word": false,
17
  "special": false
18
  },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
  "normalized": false,
23
+ "rstrip": true,
24
  "single_word": false,
25
+ "special": false
26
  },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
  "normalized": false,
31
+ "rstrip": true,
32
  "single_word": false,
33
+ "special": false
34
  }
35
  },
36
  "bos_token": "<s>",
 
39
  "eos_token": "</s>",
40
  "extra_special_tokens": {},
41
  "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<pad>",
43
  "replace_word_delimiter_char": " ",
44
  "target_lang": "tur",
45
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "<unk>",
47
  "word_delimiter_token": "|"
48
  }
vocab.json CHANGED
@@ -1,33 +1,36 @@
1
  {
2
  "tur": {
3
- "[PAD]": 28,
4
- "[UNK]": 27,
5
- "a": 1,
6
- "b": 2,
7
- "c": 3,
8
- "d": 4,
9
- "e": 5,
10
- "f": 6,
11
- "g": 7,
12
- "h": 8,
13
- "i": 9,
14
- "j": 10,
15
- "k": 11,
16
- "l": 12,
 
 
 
17
  "m": 13,
18
- "n": 14,
19
- "o": 15,
20
- "p": 16,
21
- "q": 17,
22
- "r": 18,
23
- "s": 19,
24
- "t": 20,
25
- "u": 21,
26
- "v": 22,
27
- "w": 23,
28
- "x": 24,
29
- "y": 25,
30
- "z": 26,
31
- "|": 0
32
  }
33
  }
 
1
  {
2
  "tur": {
3
+ "'": 26,
4
+ "</s>": 2,
5
+ "<pad>": 0,
6
+ "<s>": 1,
7
+ "<unk>": 3,
8
+ "a": 5,
9
+ "b": 21,
10
+ "c": 23,
11
+ "d": 19,
12
+ "e": 7,
13
+ "f": 29,
14
+ "g": 18,
15
+ "h": 17,
16
+ "i": 6,
17
+ "j": 25,
18
+ "k": 12,
19
+ "l": 16,
20
  "m": 13,
21
+ "n": 8,
22
+ "o": 9,
23
+ "p": 22,
24
+ "q": 30,
25
+ "r": 15,
26
+ "s": 14,
27
+ "t": 11,
28
+ "u": 10,
29
+ "v": 27,
30
+ "w": 24,
31
+ "x": 31,
32
+ "y": 20,
33
+ "z": 28,
34
+ "|": 4
35
  }
36
  }