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
6c7c5e1
•
1 Parent(s): ba5b84b

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer_config.json +6 -5
  2. vocab.json +59 -59
tokenizer_config.json CHANGED
@@ -1,13 +1,14 @@
1
  {
2
  "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
4
- "do_lower_case": false,
5
  "eos_token": "</s>",
6
  "model_max_length": 1000000000000000019884624838656,
7
  "pad_token": "[PAD]",
8
- "replace_word_delimiter_char": " ",
9
- "target_lang": null,
10
- "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
11
  "unk_token": "[UNK]",
12
- "word_delimiter_token": "|"
13
  }
 
1
  {
2
  "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
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": 56,
5
- "ae": 46,
6
- "ah": 37,
7
- "ao": 31,
8
- "aw": 17,
9
- "ax": 12,
10
- "ax-h": 29,
11
- "axr": 49,
12
- "ay": 32,
13
  "b": 30,
14
- "bcl": 8,
15
- "ch": 21,
16
- "d": 44,
17
- "dcl": 47,
18
- "dh": 5,
19
- "dx": 13,
20
- "eh": 38,
21
- "el": 15,
22
- "em": 14,
23
- "en": 53,
24
- "eng": 48,
25
- "epi": 22,
26
- "er": 1,
27
- "ey": 33,
28
- "f": 16,
29
- "g": 58,
30
- "gcl": 7,
31
- "h#": 0,
32
- "hh": 41,
33
- "hv": 18,
34
- "ih": 28,
35
- "ix": 19,
36
- "iy": 57,
37
- "jh": 39,
38
- "k": 3,
39
- "kcl": 9,
40
- "l": 20,
41
- "m": 25,
42
- "n": 51,
43
- "ng": 55,
44
- "nx": 43,
45
- "ow": 52,
46
- "oy": 54,
47
- "p": 45,
48
- "pau": 40,
49
- "pcl": 6,
50
- "q": 60,
51
- "r": 23,
52
- "s": 4,
53
- "sh": 36,
54
- "t": 11,
55
- "tcl": 10,
56
- "th": 27,
57
- "uh": 42,
58
- "uw": 24,
59
  "ux": 50,
60
- "v": 26,
61
- "w": 2,
62
- "y": 35,
63
- "z": 59,
64
- "zh": 34,
65
  "|": 61
66
  }
 
1
  {
2
  "[PAD]": 63,
3
  "[UNK]": 62,
4
+ "aa": 52,
5
+ "ae": 6,
6
+ "ah": 57,
7
+ "ao": 28,
8
+ "aw": 20,
9
+ "ax": 45,
10
+ "ax-h": 60,
11
+ "axr": 15,
12
+ "ay": 4,
13
  "b": 30,
14
+ "bcl": 37,
15
+ "ch": 12,
16
+ "d": 22,
17
+ "dcl": 43,
18
+ "dh": 1,
19
+ "dx": 26,
20
+ "eh": 33,
21
+ "el": 56,
22
+ "em": 24,
23
+ "en": 39,
24
+ "eng": 31,
25
+ "epi": 36,
26
+ "er": 8,
27
+ "ey": 29,
28
+ "f": 54,
29
+ "g": 47,
30
+ "gcl": 34,
31
+ "h#": 7,
32
+ "hh": 59,
33
+ "hv": 42,
34
+ "ih": 14,
35
+ "ix": 10,
36
+ "iy": 40,
37
+ "jh": 41,
38
+ "k": 48,
39
+ "kcl": 44,
40
+ "l": 9,
41
+ "m": 38,
42
+ "n": 13,
43
+ "ng": 23,
44
+ "nx": 25,
45
+ "ow": 53,
46
+ "oy": 17,
47
+ "p": 55,
48
+ "pau": 58,
49
+ "pcl": 2,
50
+ "q": 11,
51
+ "r": 35,
52
+ "s": 18,
53
+ "sh": 49,
54
+ "t": 27,
55
+ "tcl": 19,
56
+ "th": 16,
57
+ "uh": 3,
58
+ "uw": 5,
59
  "ux": 50,
60
+ "v": 32,
61
+ "w": 0,
62
+ "y": 51,
63
+ "z": 46,
64
+ "zh": 21,
65
  "|": 61
66
  }