Hugging Face's logo

aaniket
/
wav2vec2-large-xlsr-phoneme-recongition

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
aaniket commited on
Commit
aede03a
•
1 Parent(s): 96dd8dc

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +2 -2
  2. tokenizer_config.json +2 -2
  3. vocab.json +56 -56
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
@@ -4,11 +4,11 @@
4
  "do_phonemize": true,
5
  "eos_token": "</s>",
6
  "model_max_length": 1000000000000000019884624838656,
7
- "pad_token": "[PAD]",
8
  "phone_delimiter_token": " ",
9
  "phonemizer_backend": "espeak",
10
  "phonemizer_lang": "en-us",
11
  "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
12
- "unk_token": "[UNK]",
13
  "word_delimiter_token": null
14
  }
 
4
  "do_phonemize": true,
5
  "eos_token": "</s>",
6
  "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
  "phone_delimiter_token": " ",
9
  "phonemizer_backend": "espeak",
10
  "phonemizer_lang": "en-us",
11
  "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
12
+ "unk_token": "<unk>",
13
  "word_delimiter_token": null
14
  }
vocab.json CHANGED
@@ -1,66 +1,66 @@
1
  {
2
  "[PAD]": 63,
3
  "[UNK]": 62,
4
- "aa": 42,
5
- "ae": 27,
6
- "ah": 33,
7
- "ao": 41,
8
- "aw": 3,
9
- "ax": 8,
10
  "ax-h": 1,
11
- "axr": 52,
12
- "ay": 32,
13
- "b": 4,
14
- "bcl": 10,
15
- "ch": 36,
16
- "d": 18,
17
- "dcl": 28,
18
- "dh": 6,
19
- "dx": 45,
20
- "eh": 2,
21
- "el": 29,
22
- "em": 19,
23
- "en": 14,
24
- "eng": 12,
25
- "epi": 58,
26
- "er": 30,
27
- "ey": 50,
28
  "f": 37,
29
- "g": 40,
30
- "gcl": 15,
31
- "h#": 49,
32
- "hh": 38,
33
- "hv": 57,
34
- "ih": 48,
35
- "ix": 43,
36
- "iy": 22,
37
- "jh": 7,
38
- "k": 53,
39
  "kcl": 23,
40
- "l": 25,
41
- "m": 51,
42
- "n": 54,
43
- "ng": 0,
44
- "nx": 9,
45
  "ow": 59,
46
- "oy": 20,
47
- "p": 11,
48
- "pau": 34,
49
- "pcl": 47,
50
- "q": 26,
51
  "r": 39,
52
- "s": 5,
53
- "sh": 17,
54
- "t": 31,
55
- "tcl": 21,
56
- "th": 55,
57
- "uh": 60,
58
- "uw": 56,
59
- "ux": 46,
60
- "v": 13,
61
- "w": 24,
62
- "y": 16,
63
- "z": 44,
64
- "zh": 35,
65
  "|": 61
66
  }
 
1
  {
2
  "[PAD]": 63,
3
  "[UNK]": 62,
4
+ "aa": 0,
5
+ "ae": 9,
6
+ "ah": 25,
7
+ "ao": 8,
8
+ "aw": 21,
9
+ "ax": 15,
10
  "ax-h": 1,
11
+ "axr": 53,
12
+ "ay": 41,
13
+ "b": 14,
14
+ "bcl": 60,
15
+ "ch": 28,
16
+ "d": 17,
17
+ "dcl": 12,
18
+ "dh": 51,
19
+ "dx": 56,
20
+ "eh": 4,
21
+ "el": 31,
22
+ "em": 49,
23
+ "en": 46,
24
+ "eng": 20,
25
+ "epi": 48,
26
+ "er": 24,
27
+ "ey": 57,
28
  "f": 37,
29
+ "g": 38,
30
+ "gcl": 32,
31
+ "h#": 19,
32
+ "hh": 55,
33
+ "hv": 29,
34
+ "ih": 35,
35
+ "ix": 40,
36
+ "iy": 33,
37
+ "jh": 5,
38
+ "k": 13,
39
  "kcl": 23,
40
+ "l": 36,
41
+ "m": 44,
42
+ "n": 30,
43
+ "ng": 50,
44
+ "nx": 27,
45
  "ow": 59,
46
+ "oy": 54,
47
+ "p": 10,
48
+ "pau": 47,
49
+ "pcl": 45,
50
+ "q": 42,
51
  "r": 39,
52
+ "s": 22,
53
+ "sh": 11,
54
+ "t": 16,
55
+ "tcl": 2,
56
+ "th": 18,
57
+ "uh": 7,
58
+ "uw": 52,
59
+ "ux": 6,
60
+ "v": 26,
61
+ "w": 34,
62
+ "y": 43,
63
+ "z": 3,
64
+ "zh": 58,
65
  "|": 61
66
  }