Hugging Face's logo

AhunInteligence
/
hubert_5k_raw_s3_pre

Feature Extraction
Transformers
Safetensors
hubert
Model card Files
xet
 Community
AhunInteligence commited on
Commit
efe7084
·
verified ·
1 Parent(s): 10a2098

Upload processor

Browse files
Files changed (5) hide show
  1. added_tokens.json +4 -0
  2. preprocessor_config.json +2 -1
  3. special_tokens_map.json +6 -0
  4. tokenizer_config.json +48 -0
  5. vocab.json +215 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 214,
3
+ "<s>": 213
4
+ }
preprocessor_config.json CHANGED
@@ -4,6 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
7
- "return_attention_mask": false,
 
8
  "sampling_rate": 16000
9
  }
 
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
  "sampling_rate": 16000
10
  }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "211": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "212": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "213": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "214": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "processor_class": "Wav2Vec2Processor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "[UNK]",
47
+ "word_delimiter_token": "|"
48
+ }
vocab.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 212,
3
+ "[UNK]": 211,
4
+ "|": 0,
5
+ "ሀ": 1,
6
+ "ሁ": 2,
7
+ "ሂ": 3,
8
+ "ሃ": 4,
9
+ "ሄ": 5,
10
+ "ህ": 6,
11
+ "ሆ": 7,
12
+ "ለ": 8,
13
+ "ሉ": 9,
14
+ "ሊ": 10,
15
+ "ላ": 11,
16
+ "ሌ": 12,
17
+ "ል": 13,
18
+ "ሎ": 14,
19
+ "ሏ": 15,
20
+ "ሗ": 16,
21
+ "መ": 17,
22
+ "ሙ": 18,
23
+ "ሚ": 19,
24
+ "ማ": 20,
25
+ "ሜ": 21,
26
+ "ም": 22,
27
+ "ሞ": 23,
28
+ "ሟ": 24,
29
+ "ረ": 25,
30
+ "ሩ": 26,
31
+ "ሪ": 27,
32
+ "ራ": 28,
33
+ "ሬ": 29,
34
+ "ር": 30,
35
+ "ሮ": 31,
36
+ "ሯ": 32,
37
+ "ሰ": 33,
38
+ "ሱ": 34,
39
+ "ሲ": 35,
40
+ "ሳ": 36,
41
+ "ሴ": 37,
42
+ "ስ": 38,
43
+ "ሶ": 39,
44
+ "ሷ": 40,
45
+ "ሸ": 41,
46
+ "ሹ": 42,
47
+ "ሺ": 43,
48
+ "ሻ": 44,
49
+ "ሼ": 45,
50
+ "ሽ": 46,
51
+ "ሾ": 47,
52
+ "ሿ": 48,
53
+ "ቀ": 49,
54
+ "ቁ": 50,
55
+ "ቂ": 51,
56
+ "ቃ": 52,
57
+ "ቄ": 53,
58
+ "ቅ": 54,
59
+ "ቆ": 55,
60
+ "ቋ": 56,
61
+ "በ": 57,
62
+ "ቡ": 58,
63
+ "ቢ": 59,
64
+ "ባ": 60,
65
+ "ቤ": 61,
66
+ "ብ": 62,
67
+ "ቦ": 63,
68
+ "ቧ": 64,
69
+ "ቨ": 65,
70
+ "ቩ": 66,
71
+ "ቪ": 67,
72
+ "ቫ": 68,
73
+ "ቬ": 69,
74
+ "ቭ": 70,
75
+ "ቮ": 71,
76
+ "ተ": 72,
77
+ "ቱ": 73,
78
+ "ቲ": 74,
79
+ "ታ": 75,
80
+ "ቴ": 76,
81
+ "ት": 77,
82
+ "ቶ": 78,
83
+ "ቷ": 79,
84
+ "ቸ": 80,
85
+ "ቹ": 81,
86
+ "ቺ": 82,
87
+ "ቻ": 83,
88
+ "ቼ": 84,
89
+ "ች": 85,
90
+ "ቾ": 86,
91
+ "ቿ": 87,
92
+ "ነ": 88,
93
+ "ኑ": 89,
94
+ "ኒ": 90,
95
+ "ና": 91,
96
+ "ኔ": 92,
97
+ "ን": 93,
98
+ "ኖ": 94,
99
+ "ኗ": 95,
100
+ "ኘ": 96,
101
+ "ኙ": 97,
102
+ "ኚ": 98,
103
+ "ኛ": 99,
104
+ "ኜ": 100,
105
+ "ኝ": 101,
106
+ "ኞ": 102,
107
+ "አ": 103,
108
+ "ኡ": 104,
109
+ "ኢ": 105,
110
+ "ኤ": 106,
111
+ "እ": 107,
112
+ "ኦ": 108,
113
+ "ከ": 109,
114
+ "ኩ": 110,
115
+ "ኪ": 111,
116
+ "ካ": 112,
117
+ "ኬ": 113,
118
+ "ክ": 114,
119
+ "ኮ": 115,
120
+ "ኳ": 116,
121
+ "ኸ": 117,
122
+ "ወ": 118,
123
+ "ዉ": 119,
124
+ "ዊ": 120,
125
+ "ዋ": 121,
126
+ "ዌ": 122,
127
+ "ው": 123,
128
+ "ዎ": 124,
129
+ "ዘ": 125,
130
+ "ዙ": 126,
131
+ "ዚ": 127,
132
+ "ዛ": 128,
133
+ "ዜ": 129,
134
+ "ዝ": 130,
135
+ "ዞ": 131,
136
+ "ዟ": 132,
137
+ "ዠ": 133,
138
+ "ዡ": 134,
139
+ "ዢ": 135,
140
+ "ዣ": 136,
141
+ "ዤ": 137,
142
+ "ዥ": 138,
143
+ "የ": 139,
144
+ "ዩ": 140,
145
+ "ዪ": 141,
146
+ "ያ": 142,
147
+ "ዬ": 143,
148
+ "ይ": 144,
149
+ "ዮ": 145,
150
+ "ደ": 146,
151
+ "ዱ": 147,
152
+ "ዲ": 148,
153
+ "ዳ": 149,
154
+ "ዴ": 150,
155
+ "ድ": 151,
156
+ "ዶ": 152,
157
+ "ዷ": 153,
158
+ "ጀ": 154,
159
+ "ጁ": 155,
160
+ "ጂ": 156,
161
+ "ጃ": 157,
162
+ "ጄ": 158,
163
+ "ጅ": 159,
164
+ "ጆ": 160,
165
+ "ገ": 161,
166
+ "ጉ": 162,
167
+ "ጊ": 163,
168
+ "ጋ": 164,
169
+ "ጌ": 165,
170
+ "ግ": 166,
171
+ "ጎ": 167,
172
+ "ጓ": 168,
173
+ "ጠ": 169,
174
+ "ጡ": 170,
175
+ "ጢ": 171,
176
+ "ጣ": 172,
177
+ "ጤ": 173,
178
+ "ጥ": 174,
179
+ "ጦ": 175,
180
+ "ጧ": 176,
181
+ "ጨ": 177,
182
+ "ጩ": 178,
183
+ "ጪ": 179,
184
+ "ጫ": 180,
185
+ "ጬ": 181,
186
+ "ጭ": 182,
187
+ "ጮ": 183,
188
+ "ጲ": 184,
189
+ "ጳ": 185,
190
+ "ጴ": 186,
191
+ "ጵ": 187,
192
+ "ጸ": 188,
193
+ "ጹ": 189,
194
+ "ጺ": 190,
195
+ "ጻ": 191,
196
+ "ጼ": 192,
197
+ "ጽ": 193,
198
+ "ጾ": 194,
199
+ "ጿ": 195,
200
+ "ፈ": 196,
201
+ "ፉ": 197,
202
+ "ፊ": 198,
203
+ "ፋ": 199,
204
+ "ፌ": 200,
205
+ "ፍ": 201,
206
+ "ፎ": 202,
207
+ "ፏ": 203,
208
+ "ፐ": 204,
209
+ "ፑ": 205,
210
+ "ፒ": 206,
211
+ "ፓ": 207,
212
+ "ፔ": 208,
213
+ "ፕ": 209,
214
+ "ፖ": 210
215
+ }