Hugging Face's logo

Piranav
/
wav2vec2-large-mms-1b-mundari-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Piranav commited on
Commit
07c4721
·
verified ·
1 Parent(s): b843f06

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. added_tokens.json +4 -2
  3. tokenizer_config.json +17 -17
  4. vocab.json +164 -70
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: cc-by-nc-4.0
3
- base_model: facebook/mms-1b-all
4
  tags:
5
  - generated_from_trainer
 
6
  datasets:
7
  - audiofolder
8
  model-index:
 
1
  ---
2
  license: cc-by-nc-4.0
 
3
  tags:
4
  - generated_from_trainer
5
+ base_model: facebook/mms-1b-all
6
  datasets:
7
  - audiofolder
8
  model-index:
added_tokens.json CHANGED
@@ -1,4 +1,6 @@
1
  {
2
- "</s>": 70,
3
- "<s>": 69
 
 
4
  }
 
1
  {
2
+ "</s>": 164,
3
+ "<s>": 163,
4
+ "[PAD]": 166,
5
+ "[UNK]": 165
6
  }
tokenizer_config.json CHANGED
@@ -1,33 +1,33 @@
1
  {
2
  "added_tokens_decoder": {
3
- "67": {
4
- "content": "[UNK]",
5
- "lstrip": true,
6
  "normalized": false,
7
- "rstrip": true,
8
  "single_word": false,
9
- "special": false
10
  },
11
- "68": {
12
- "content": "[PAD]",
13
- "lstrip": true,
14
  "normalized": false,
15
- "rstrip": true,
16
  "single_word": false,
17
- "special": false
18
  },
19
- "69": {
20
- "content": "<s>",
21
  "lstrip": false,
22
- "normalized": true,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "70": {
28
- "content": "</s>",
29
  "lstrip": false,
30
- "normalized": true,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
@@ -40,7 +40,7 @@
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
42
  "replace_word_delimiter_char": " ",
43
- "target_lang": "muw",
44
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
  "unk_token": "[UNK]",
46
  "word_delimiter_token": "|"
 
1
  {
2
  "added_tokens_decoder": {
3
+ "163": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
  "normalized": false,
7
+ "rstrip": false,
8
  "single_word": false,
9
+ "special": true
10
  },
11
+ "164": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
  "normalized": false,
15
+ "rstrip": false,
16
  "single_word": false,
17
+ "special": true
18
  },
19
+ "165": {
20
+ "content": "[UNK]",
21
  "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "166": {
28
+ "content": "[PAD]",
29
  "lstrip": false,
30
+ "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
 
40
  "model_max_length": 1000000000000000019884624838656,
41
  "pad_token": "[PAD]",
42
  "replace_word_delimiter_char": " ",
43
+ "target_lang": "unr",
44
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
  "unk_token": "[UNK]",
46
  "word_delimiter_token": "|"
vocab.json CHANGED
@@ -1,73 +1,167 @@
1
  {
2
- "muw": {
3
- "(": 1,
4
- ")": 2,
5
- ",": 3,
6
- "-": 4,
7
- ":": 5,
8
- "?": 6,
9
- "[PAD]": 68,
10
- "[UNK]": 67,
11
- "|": 0,
12
- "ं": 7,
13
- "ः": 8,
14
- "अ": 9,
15
- "आ": 10,
16
- "इ": 11,
17
- "ई": 12,
18
- "उ": 13,
19
- "ऊ": 14,
20
- "ए": 15,
21
- "ऑ": 16,
22
- "ओ": 17,
23
- "क": 18,
24
- "ख": 19,
25
- "ग": 20,
26
- "घ": 21,
27
- "ङ": 22,
28
- "च": 23,
29
- "छ": 24,
30
- "ज": 25,
31
- "झ": 26,
32
- "ञ": 27,
33
- "ट": 28,
34
- "ठ": 29,
35
- "ड": 30,
36
- "ण": 31,
37
- "त": 32,
38
- "थ": 33,
39
- "द": 34,
40
- "ध": 35,
41
- "न": 36,
42
- "प": 37,
43
- "फ": 38,
44
- "ब": 39,
45
- "भ": 40,
46
- "म": 41,
47
- "य": 42,
48
- "र": 43,
49
- "ल": 44,
50
- "व": 45,
51
- "श": 46,
52
- "ष": 47,
53
- "स": 48,
54
- "ह": 49,
55
- "़": 50,
56
- "ा": 51,
57
- "ि": 52,
58
- "ी": 53,
59
- "ु": 54,
60
- "ू": 55,
61
- "ृ": 56,
62
- "े": 57,
63
- "ै": 58,
64
- "ॉ": 59,
65
- "ो": 60,
66
- "ौ": 61,
67
- "्": 62,
68
- "ड़": 63,
69
- "ढ़": 64,
70
- "।": 65,
71
- "‌": 66
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
  }
73
  }
 
1
  {
2
+ "unr": {
3
+ " ": 0,
4
+ "!": 1,
5
+ "'": 2,
6
+ "(": 3,
7
+ ")": 4,
8
+ "+": 5,
9
+ ",": 6,
10
+ "-": 7,
11
+ ".": 8,
12
+ "/": 9,
13
+ "0": 10,
14
+ "1": 11,
15
+ "2": 12,
16
+ "3": 13,
17
+ "4": 14,
18
+ "5": 15,
19
+ "7": 16,
20
+ "8": 17,
21
+ "9": 18,
22
+ ":": 19,
23
+ ";": 20,
24
+ "<": 21,
25
+ "=": 22,
26
+ ">": 23,
27
+ "?": 24,
28
+ "A": 25,
29
+ "B": 26,
30
+ "C": 27,
31
+ "D": 28,
32
+ "E": 29,
33
+ "F": 30,
34
+ "G": 31,
35
+ "H": 32,
36
+ "I": 33,
37
+ "L": 34,
38
+ "M": 35,
39
+ "N": 36,
40
+ "O": 37,
41
+ "P": 38,
42
+ "R": 39,
43
+ "S": 40,
44
+ "T": 41,
45
+ "V": 42,
46
+ "X": 43,
47
+ "]": 44,
48
+ "a": 45,
49
+ "d": 46,
50
+ "e": 47,
51
+ "g": 48,
52
+ "i": 49,
53
+ "l": 50,
54
+ "n": 51,
55
+ "o": 52,
56
+ "p": 53,
57
+ "r": 54,
58
+ "t": 55,
59
+ "u": 56,
60
+ "w": 57,
61
+ "y": 58,
62
+ "|": 59,
63
+ " ": 60,
64
+ "ª": 61,
65
+ "´": 62,
66
+ "·": 63,
67
+ "́": 64,
68
+ "Б": 65,
69
+ "Г": 66,
70
+ "а": 67,
71
+ "в": 68,
72
+ "е": 69,
73
+ "з": 70,
74
+ "и": 71,
75
+ "к": 72,
76
+ "р": 73,
77
+ "у": 74,
78
+ "ш": 75,
79
+ "я": 76,
80
+ "ا": 77,
81
+ "س": 78,
82
+ "ن": 79,
83
+ "ک": 80,
84
+ "ی": 81,
85
+ "ँ": 82,
86
+ "ं": 83,
87
+ "ः": 84,
88
+ "अ": 85,
89
+ "आ": 86,
90
+ "इ": 87,
91
+ "ई": 88,
92
+ "उ": 89,
93
+ "ऊ": 90,
94
+ "ऋ": 91,
95
+ "ए": 92,
96
+ "ऐ": 93,
97
+ "ऑ": 94,
98
+ "ओ": 95,
99
+ "औ": 96,
100
+ "क": 97,
101
+ "ख": 98,
102
+ "ग": 99,
103
+ "घ": 100,
104
+ "ङ": 101,
105
+ "च": 102,
106
+ "छ": 103,
107
+ "ज": 104,
108
+ "झ": 105,
109
+ "ञ": 106,
110
+ "ट": 107,
111
+ "ठ": 108,
112
+ "ड": 109,
113
+ "ढ": 110,
114
+ "ण": 111,
115
+ "त": 112,
116
+ "थ": 113,
117
+ "द": 114,
118
+ "ध": 115,
119
+ "न": 116,
120
+ "प": 117,
121
+ "फ": 118,
122
+ "ब": 119,
123
+ "भ": 120,
124
+ "म": 121,
125
+ "य": 122,
126
+ "र": 123,
127
+ "ऱ": 124,
128
+ "ल": 125,
129
+ "व": 126,
130
+ "श": 127,
131
+ "ष": 128,
132
+ "स": 129,
133
+ "ह": 130,
134
+ "ऺ": 131,
135
+ "़": 132,
136
+ "ऽ": 133,
137
+ "ा": 134,
138
+ "ि": 135,
139
+ "ी": 136,
140
+ "ु": 137,
141
+ "ू": 138,
142
+ "ृ": 139,
143
+ "ॅ": 140,
144
+ "े": 141,
145
+ "ै": 142,
146
+ "ॉ": 143,
147
+ "ॊ": 144,
148
+ "ो": 145,
149
+ "ौ": 146,
150
+ "्": 147,
151
+ "ॐ": 148,
152
+ "क़": 149,
153
+ "ख़": 150,
154
+ "ग़": 151,
155
+ "ज़": 152,
156
+ "ड़": 153,
157
+ "ढ़": 154,
158
+ "फ़": 155,
159
+ "ॢ": 156,
160
+ "।": 157,
161
+ "॥": 158,
162
+ "‌": 159,
163
+ "‍": 160,
164
+ "–": 161,
165
+ "’": 162
166
  }
167
  }