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
9e00df1
•
1 Parent(s): c310ef1

Upload tokenizer

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