Hugging Face's logo

projecti7
/
wav2vec2-amharic-merged

Safetensors
wav2vec2
Model card Files
xet
 Community
projecti7 commited on
Commit
e9e68d4
·
verified ·
1 Parent(s): 4a77def

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. config.json +116 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +10 -0
  4. special_tokens_map.json +30 -0
  5. tokenizer_config.json +49 -0
  6. vocab.json +236 -0
config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "adapter_attn_dim": null,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "dtype": "float32",
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.1,
64
+ "mask_channel_length": 10,
65
+ "mask_channel_min_space": 1,
66
+ "mask_channel_other": 0.0,
67
+ "mask_channel_prob": 0.0,
68
+ "mask_channel_selection": "static",
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_min_space": 1,
75
+ "mask_time_other": 0.0,
76
+ "mask_time_prob": 0.075,
77
+ "mask_time_selection": "static",
78
+ "model_type": "wav2vec2",
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 16,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 24,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 1024,
89
+ "pad_token_id": 0,
90
+ "proj_codevector_dim": 768,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "transformers_version": "4.57.2",
113
+ "use_weighted_layer_sum": false,
114
+ "vocab_size": 234,
115
+ "xvector_output_dim": 512
116
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60edbc70122465487a71706a2bb9a0282fc89b6d25dfcfd53c7ef12bf89a7d64
3
+ size 1262766880
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": true,
5
+ "normalized": false,
6
+ "rstrip": true,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": true,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<pad>",
43
+ "processor_class": "Wav2Vec2Processor",
44
+ "replace_word_delimiter_char": " ",
45
+ "target_lang": null,
46
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
47
+ "unk_token": "<unk>",
48
+ "word_delimiter_token": "|"
49
+ }
vocab.json ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 4,
3
+ "</s>": 2,
4
+ "<pad>": 0,
5
+ "<s>": 1,
6
+ "<unk>": 3,
7
+ "ሀ": 5,
8
+ "ሁ": 6,
9
+ "ሂ": 7,
10
+ "ሃ": 8,
11
+ "ሄ": 9,
12
+ "ህ": 10,
13
+ "ሆ": 11,
14
+ "ለ": 12,
15
+ "ሉ": 13,
16
+ "ሊ": 14,
17
+ "ላ": 15,
18
+ "ሌ": 16,
19
+ "ል": 17,
20
+ "ሎ": 18,
21
+ "ሏ": 19,
22
+ "መ": 20,
23
+ "ሙ": 21,
24
+ "ሚ": 22,
25
+ "ማ": 23,
26
+ "ሜ": 24,
27
+ "ም": 25,
28
+ "ሞ": 26,
29
+ "ሟ": 27,
30
+ "ረ": 28,
31
+ "ሩ": 29,
32
+ "ሪ": 30,
33
+ "ራ": 31,
34
+ "ሬ": 32,
35
+ "ር": 33,
36
+ "ሮ": 34,
37
+ "ሯ": 35,
38
+ "ሰ": 36,
39
+ "ሱ": 37,
40
+ "ሲ": 38,
41
+ "ሳ": 39,
42
+ "ሴ": 40,
43
+ "ስ": 41,
44
+ "ሶ": 42,
45
+ "ሷ": 43,
46
+ "ሸ": 44,
47
+ "ሹ": 45,
48
+ "ሺ": 46,
49
+ "ሻ": 47,
50
+ "ሼ": 48,
51
+ "ሽ": 49,
52
+ "ሾ": 50,
53
+ "ሿ": 51,
54
+ "ቀ": 52,
55
+ "ቁ": 53,
56
+ "ቂ": 54,
57
+ "ቃ": 55,
58
+ "ቄ": 56,
59
+ "ቅ": 57,
60
+ "ቆ": 58,
61
+ "ቋ": 59,
62
+ "በ": 60,
63
+ "ቡ": 61,
64
+ "ቢ": 62,
65
+ "ባ": 63,
66
+ "ቤ": 64,
67
+ "ብ": 65,
68
+ "ቦ": 66,
69
+ "ቧ": 67,
70
+ "ቨ": 68,
71
+ "ቩ": 69,
72
+ "ቪ": 70,
73
+ "ቫ": 71,
74
+ "ቬ": 72,
75
+ "ቭ": 73,
76
+ "ቮ": 74,
77
+ "ቯ": 75,
78
+ "ተ": 76,
79
+ "ቱ": 77,
80
+ "ቲ": 78,
81
+ "ታ": 79,
82
+ "ቴ": 80,
83
+ "ት": 81,
84
+ "ቶ": 82,
85
+ "ቷ": 83,
86
+ "ቸ": 84,
87
+ "ቹ": 85,
88
+ "ቺ": 86,
89
+ "ቻ": 87,
90
+ "ቼ": 88,
91
+ "ች": 89,
92
+ "ቾ": 90,
93
+ "ቿ": 91,
94
+ "ኋ": 92,
95
+ "ነ": 93,
96
+ "ኑ": 94,
97
+ "ኒ": 95,
98
+ "ና": 96,
99
+ "ኔ": 97,
100
+ "ን": 98,
101
+ "ኖ": 99,
102
+ "ኗ": 100,
103
+ "ኘ": 101,
104
+ "ኙ": 102,
105
+ "ኚ": 103,
106
+ "ኛ": 104,
107
+ "ኜ": 105,
108
+ "ኝ": 106,
109
+ "ኞ": 107,
110
+ "ኟ": 108,
111
+ "አ": 109,
112
+ "ኡ": 110,
113
+ "ኢ": 111,
114
+ "ኣ": 112,
115
+ "ኤ": 113,
116
+ "እ": 114,
117
+ "ኦ": 115,
118
+ "ከ": 116,
119
+ "ኩ": 117,
120
+ "ኪ": 118,
121
+ "ካ": 119,
122
+ "ኬ": 120,
123
+ "ክ": 121,
124
+ "ኮ": 122,
125
+ "ኰ": 123,
126
+ "ኲ": 124,
127
+ "ኳ": 125,
128
+ "ኸ": 126,
129
+ "ወ": 127,
130
+ "ዉ": 128,
131
+ "ዊ": 129,
132
+ "ዋ": 130,
133
+ "ዌ": 131,
134
+ "ው": 132,
135
+ "ዎ": 133,
136
+ "ዘ": 134,
137
+ "ዙ": 135,
138
+ "ዚ": 136,
139
+ "ዛ": 137,
140
+ "ዜ": 138,
141
+ "ዝ": 139,
142
+ "ዞ": 140,
143
+ "ዟ": 141,
144
+ "ዠ": 142,
145
+ "ዡ": 143,
146
+ "ዢ": 144,
147
+ "ዣ": 145,
148
+ "ዤ": 146,
149
+ "ዥ": 147,
150
+ "ዦ": 148,
151
+ "ዧ": 149,
152
+ "የ": 150,
153
+ "ዩ": 151,
154
+ "ዪ": 152,
155
+ "ያ": 153,
156
+ "ዬ": 154,
157
+ "ይ": 155,
158
+ "ዮ": 156,
159
+ "ደ": 157,
160
+ "ዱ": 158,
161
+ "ዲ": 159,
162
+ "ዳ": 160,
163
+ "ዴ": 161,
164
+ "ድ": 162,
165
+ "ዶ": 163,
166
+ "ዷ": 164,
167
+ "ዸ": 165,
168
+ "ዺ": 166,
169
+ "ዻ": 167,
170
+ "ዼ": 168,
171
+ "ዽ": 169,
172
+ "ዾ": 170,
173
+ "ጀ": 171,
174
+ "ጁ": 172,
175
+ "ጂ": 173,
176
+ "ጃ": 174,
177
+ "ጄ": 175,
178
+ "ጅ": 176,
179
+ "ጆ": 177,
180
+ "ጇ": 178,
181
+ "ገ": 179,
182
+ "ጉ": 180,
183
+ "ጊ": 181,
184
+ "ጋ": 182,
185
+ "ጌ": 183,
186
+ "ግ": 184,
187
+ "ጐ": 185,
188
+ "ጓ": 186,
189
+ "ጔ": 187,
190
+ "ጠ": 188,
191
+ "ጡ": 189,
192
+ "ጢ": 190,
193
+ "ጣ": 191,
194
+ "ጤ": 192,
195
+ "ጥ": 193,
196
+ "ጦ": 194,
197
+ "ጧ": 195,
198
+ "ጨ": 196,
199
+ "ጩ": 197,
200
+ "ጪ": 198,
201
+ "ጫ": 199,
202
+ "ጬ": 200,
203
+ "ጭ": 201,
204
+ "ጮ": 202,
205
+ "ጯ": 203,
206
+ "ጰ": 204,
207
+ "ጱ": 205,
208
+ "ጲ": 206,
209
+ "ጳ": 207,
210
+ "ጴ": 208,
211
+ "ጵ": 209,
212
+ "ጶ": 210,
213
+ "ጸ": 211,
214
+ "ጹ": 212,
215
+ "ጺ": 213,
216
+ "ጻ": 214,
217
+ "ጼ": 215,
218
+ "ጽ": 216,
219
+ "ጾ": 217,
220
+ "ጿ": 218,
221
+ "ፈ": 219,
222
+ "ፉ": 220,
223
+ "ፊ": 221,
224
+ "ፋ": 222,
225
+ "ፌ": 223,
226
+ "ፍ": 224,
227
+ "ፎ": 225,
228
+ "ፏ": 226,
229
+ "ፐ": 227,
230
+ "ፑ": 228,
231
+ "ፒ": 229,
232
+ "ፓ": 230,
233
+ "ፔ": 231,
234
+ "ፕ": 232,
235
+ "ፖ": 233
236
+ }