Hugging Face's logo

EricLeonhard11
/
wav2vec2-large-xls-r-300m-turkish-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
EricLeonhard11 commited on
Commit
4855814
•
1 Parent(s): 25f0213

Upload tokenizer

Browse files
Files changed (2) hide show
  1. added_tokens.json +2 -2
  2. vocab.json +227 -72
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 74,
3
- "<s>": 73
4
  }
 
1
  {
2
+ "</s>": 228,
3
+ "<s>": 227
4
  }
vocab.json CHANGED
@@ -1,75 +1,230 @@
1
  {
2
- "[PAD]": 72,
3
- "[UNK]": 71,
4
- "a": 1,
5
- "e": 2,
6
- "f": 3,
7
- "i": 4,
8
- "l": 5,
9
- "m": 6,
10
- "p": 7,
11
- "r": 8,
12
- "u": 9,
13
- "w": 10,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "|": 0,
15
- "ँ": 11,
16
- "ं": 12,
17
- "ः": 13,
18
- "अ": 14,
19
- "आ": 15,
20
- "इ": 16,
21
- "ई": 17,
22
- "उ": 18,
23
- "ऊ": 19,
24
- "ए": 20,
25
- "ऐ": 21,
26
- "ऑ": 22,
27
- "ओ": 23,
28
- "औ": 24,
29
- "क": 25,
30
- "ख": 26,
31
- "ग": 27,
32
- "घ": 28,
33
- "च": 29,
34
- "छ": 30,
35
- "ज": 31,
36
- "झ": 32,
37
- "ट": 33,
38
- "ठ": 34,
39
- "ड": 35,
40
- "ढ": 36,
41
- "ण": 37,
42
- "त": 38,
43
- "थ": 39,
44
- "द": 40,
45
- "ध": 41,
46
- "न": 42,
47
- "प": 43,
48
- "फ": 44,
49
- "ब": 45,
50
- "भ": 46,
51
- "म": 47,
52
- "य": 48,
53
- "र": 49,
54
- "ल": 50,
55
- "व": 51,
56
- "श": 52,
57
- "ष": 53,
58
- "स": 54,
59
- "ह": 55,
60
- "़": 56,
61
- "ा": 57,
62
- "ि": 58,
63
- "ी": 59,
64
- "ु": 60,
65
- "ू": 61,
66
- "ृ": 62,
67
- "े": 63,
68
- "ै": 64,
69
- "ॉ": 65,
70
- "ो": 66,
71
- "ौ": 67,
72
- "्": 68,
73
- "ड़": 69,
74
- "।": 70
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  }
 
1
  {
2
+ "$": 1,
3
+ "&": 2,
4
+ "=": 3,
5
+ "[PAD]": 227,
6
+ "[UNK]": 226,
7
+ "_": 4,
8
+ "`": 5,
9
+ "a": 6,
10
+ "b": 7,
11
+ "c": 8,
12
+ "d": 9,
13
+ "e": 10,
14
+ "f": 11,
15
+ "g": 12,
16
+ "h": 13,
17
+ "i": 14,
18
+ "j": 15,
19
+ "k": 16,
20
+ "l": 17,
21
+ "m": 18,
22
+ "n": 19,
23
+ "o": 20,
24
+ "p": 21,
25
+ "q": 22,
26
+ "r": 23,
27
+ "s": 24,
28
+ "t": 25,
29
+ "u": 26,
30
+ "v": 27,
31
+ "w": 28,
32
+ "x": 29,
33
+ "y": 30,
34
+ "z": 31,
35
+ "{": 32,
36
  "|": 0,
37
+ "}": 34,
38
+ "~": 35,
39
+ "¡": 36,
40
+ "¨": 37,
41
+ "ª": 38,
42
+ "«": 39,
43
+ "®": 40,
44
+ "°": 41,
45
+ "´": 42,
46
+ "·": 43,
47
+ "»": 44,
48
+ "¿": 45,
49
+ "ß": 46,
50
+ "à": 47,
51
+ "á": 48,
52
+ "ã": 49,
53
+ "ä": 50,
54
+ "å": 51,
55
+ "æ": 52,
56
+ "ç": 53,
57
+ "é": 54,
58
+ "ê": 55,
59
+ "ë": 56,
60
+ "ì": 57,
61
+ "í": 58,
62
+ "ï": 59,
63
+ "ð": 60,
64
+ "ñ": 61,
65
+ "ò": 62,
66
+ "ó": 63,
67
+ "õ": 64,
68
+ "ö": 65,
69
+ "ø": 66,
70
+ "ù": 67,
71
+ "ú": 68,
72
+ "ü": 69,
73
+ "ý": 70,
74
+ "þ": 71,
75
+ "ā": 72,
76
+ "ă": 73,
77
+ "ć": 74,
78
+ "č": 75,
79
+ "đ": 76,
80
+ "ė": 77,
81
+ "ę": 78,
82
+ "ě": 79,
83
+ "ğ": 80,
84
+ "ī": 81,
85
+ "ı": 82,
86
+ "ł": 83,
87
+ "ń": 84,
88
+ "ō": 85,
89
+ "ŏ": 86,
90
+ "ő": 87,
91
+ "œ": 88,
92
+ "ř": 89,
93
+ "ś": 90,
94
+ "ş": 91,
95
+ "š": 92,
96
+ "ū": 93,
97
+ "ź": 94,
98
+ "ż": 95,
99
+ "ž": 96,
100
+ "ș": 97,
101
+ "ț": 98,
102
+ "ə": 99,
103
+ "ʷ": 100,
104
+ "ʻ": 101,
105
+ "ʽ": 102,
106
+ "ʿ": 103,
107
+ "ː": 104,
108
+ "́": 105,
109
+ "̇": 106,
110
+ "ϙ": 107,
111
+ "а": 108,
112
+ "б": 109,
113
+ "в": 110,
114
+ "г": 111,
115
+ "д": 112,
116
+ "е": 113,
117
+ "и": 114,
118
+ "й": 115,
119
+ "к": 116,
120
+ "л": 117,
121
+ "н": 118,
122
+ "о": 119,
123
+ "п": 120,
124
+ "р": 121,
125
+ "с": 122,
126
+ "т": 123,
127
+ "ч": 124,
128
+ "ш": 125,
129
+ "ы": 126,
130
+ "ь": 127,
131
+ "ю": 128,
132
+ "я": 129,
133
+ "ё": 130,
134
+ "ү": 131,
135
+ "ө": 132,
136
+ "ְ": 133,
137
+ "ִ": 134,
138
+ "ֵ": 135,
139
+ "ָ": 136,
140
+ "ֹ": 137,
141
+ "ּ": 138,
142
+ "ב": 139,
143
+ "ה": 140,
144
+ "ו": 141,
145
+ "י": 142,
146
+ "כ": 143,
147
+ "ל": 144,
148
+ "ם": 145,
149
+ "מ": 146,
150
+ "נ": 147,
151
+ "ס": 148,
152
+ "ק": 149,
153
+ "ר": 150,
154
+ "ש": 151,
155
+ "ת": 152,
156
+ "ا": 153,
157
+ "ب": 154,
158
+ "ة": 155,
159
+ "د": 156,
160
+ "ذ": 157,
161
+ "ر": 158,
162
+ "ل": 159,
163
+ "م": 160,
164
+ "ه": 161,
165
+ "و": 162,
166
+ "ي": 163,
167
+ "ਆ": 164,
168
+ "ਘ": 165,
169
+ "ਤ": 166,
170
+ "ਨ": 167,
171
+ "ਮ": 168,
172
+ "ਸ": 169,
173
+ "ਾ": 170,
174
+ "ਿ": 171,
175
+ "ੰ": 172,
176
+ "ṁ": 173,
177
+ "ṃ": 174,
178
+ "ṇ": 175,
179
+ "ồ": 176,
180
+ "‐": 177,
181
+ "‑": 178,
182
+ "–": 179,
183
+ "—": 180,
184
+ "―": 181,
185
+ "’": 182,
186
+ "„": 183,
187
+ "…": 184,
188
+ "‧": 185,
189
+ "‹": 186,
190
+ "›": 187,
191
+ "→": 188,
192
+ "≪": 189,
193
+ "≫": 190,
194
+ "し": 191,
195
+ "の": 192,
196
+ "ひ": 193,
197
+ "ら": 194,
198
+ "ゴ": 195,
199
+ "ヒ": 196,
200
+ "ミ": 197,
201
+ "ム": 198,
202
+ "ラ": 199,
203
+ "㓁": 200,
204
+ "口": 201,
205
+ "周": 202,
206
+ "夷": 203,
207
+ "山": 204,
208
+ "戌": 205,
209
+ "日": 206,
210
+ "本": 207,
211
+ "比": 208,
212
+ "毵": 209,
213
+ "消": 210,
214
+ "生": 211,
215
+ "申": 212,
216
+ "真": 213,
217
+ "箱": 214,
218
+ "网": 215,
219
+ "罒": 216,
220
+ "罓": 217,
221
+ "肋": 218,
222
+ "肌": 219,
223
+ "背": 220,
224
+ "良": 221,
225
+ "蝦": 222,
226
+ "鮓": 223,
227
+ "鮨": 224,
228
+ "fi": 225,
229
+ "": 226
230
  }