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
9d80e28
•
1 Parent(s): 4eebafc

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