arunasrivastava commited on
Commit
3818acc
·
1 Parent(s): 286643e
Files changed (5) hide show
  1. added_tokens.json +4 -0
  2. config copy.json +117 -0
  3. special_tokens_map.json +30 -0
  4. tokenizer_config.json +1408 -0
  5. vocab.json +313 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 312,
3
+ "<s>": 311
4
+ }
config copy.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/arunasri/ML/notebooks/results/INTERSPEECH_no_resize_noiseA_train/final_model",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "mean",
46
+ "ctc_zero_infinity": true,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
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": 0.0,
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": 4,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_min_space": 1,
75
+ "mask_time_other": 0.0,
76
+ "mask_time_prob": 0.05,
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": 310,
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
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.46.1",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 313,
116
+ "xvector_output_dim": 512
117
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
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 +1,1408 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "1": {
4
+ "content": "ɠ̊",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "3": {
12
+ "content": "ɬʼ",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "4": {
20
+ "content": "q͡ꭓ",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "5": {
28
+ "content": "ʡʼ",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "7": {
36
+ "content": "ɐ̃",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "9": {
44
+ "content": "ð̼",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "12": {
52
+ "content": "ø̞̃",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "13": {
60
+ "content": "ɓ̥",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "14": {
68
+ "content": "ɴǁ",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "17": {
76
+ "content": "ɤ̃",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "18": {
84
+ "content": "d͡ɮ",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "19": {
92
+ "content": "ɡǀ",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "21": {
100
+ "content": "kǂ",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "22": {
108
+ "content": "ʡ̆",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "26": {
116
+ "content": "θʼ",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "27": {
124
+ "content": "ŋ̊",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "28": {
132
+ "content": "n̥",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "30": {
140
+ "content": "ɻ˔",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "32": {
148
+ "content": "ɾ̼",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "33": {
156
+ "content": "ʟ̝",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "34": {
164
+ "content": "r̥",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "36": {
172
+ "content": "ɕʼ",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "37": {
180
+ "content": "qǃ",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "39": {
188
+ "content": "kʼ",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "41": {
196
+ "content": "kǀ",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "42": {
204
+ "content": "ɻ̊˔",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "43": {
212
+ "content": "t͡sʼ",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "44": {
220
+ "content": "ʈʼ",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "46": {
228
+ "content": "ø̃",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "48": {
236
+ "content": "k͡p",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "50": {
244
+ "content": "ɑ̃",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "51": {
252
+ "content": "ɵ̃",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "54": {
260
+ "content": "ɞ̃",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "56": {
268
+ "content": "ʡ͡ʜ",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "58": {
276
+ "content": "qʼ",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "59": {
284
+ "content": "ʎ̝̊",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "60": {
292
+ "content": "ɤ̞̃",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "61": {
300
+ "content": "kǁ",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "62": {
308
+ "content": "o̞",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "64": {
316
+ "content": "ɢǂ",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "66": {
324
+ "content": "c͡ç",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "67": {
332
+ "content": "ʈ͡ʂʼ",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "70": {
340
+ "content": "kǃ",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "73": {
348
+ "content": "ɜ̃",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "77": {
356
+ "content": "ɖ͡ʐ",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "78": {
364
+ "content": "ɡ͡ɣ",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "79": {
372
+ "content": "kʘ",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "81": {
380
+ "content": "ũ",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "84": {
388
+ "content": "ʎ̆",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "85": {
396
+ "content": "ɒ̃",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "86": {
404
+ "content": "ɟ͡ʝ",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "87": {
412
+ "content": "t̼",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "88": {
420
+ "content": "ɢǀ",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "89": {
428
+ "content": "k̚",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "91": {
436
+ "content": "t͡ʃ",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "94": {
444
+ "content": "d͡ʑ",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "97": {
452
+ "content": "ɪ̃",
453
+ "lstrip": true,
454
+ "normalized": false,
455
+ "rstrip": true,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "98": {
460
+ "content": "ɛ̃",
461
+ "lstrip": true,
462
+ "normalized": false,
463
+ "rstrip": true,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "100": {
468
+ "content": "θ̠",
469
+ "lstrip": true,
470
+ "normalized": false,
471
+ "rstrip": true,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "101": {
476
+ "content": "ɴǀ",
477
+ "lstrip": true,
478
+ "normalized": false,
479
+ "rstrip": true,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "103": {
484
+ "content": "p͡ɸ",
485
+ "lstrip": true,
486
+ "normalized": false,
487
+ "rstrip": true,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "105": {
492
+ "content": "p̪͡f",
493
+ "lstrip": true,
494
+ "normalized": false,
495
+ "rstrip": true,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "107": {
500
+ "content": "ɢʘ",
501
+ "lstrip": true,
502
+ "normalized": false,
503
+ "rstrip": true,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "108": {
508
+ "content": "t͡ʃʼ",
509
+ "lstrip": true,
510
+ "normalized": false,
511
+ "rstrip": true,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "109": {
516
+ "content": "ɨ̃",
517
+ "lstrip": true,
518
+ "normalized": false,
519
+ "rstrip": true,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "110": {
524
+ "content": "ʂʼ",
525
+ "lstrip": true,
526
+ "normalized": false,
527
+ "rstrip": true,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "111": {
532
+ "content": "ɢ͡ʁ",
533
+ "lstrip": true,
534
+ "normalized": false,
535
+ "rstrip": true,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "112": {
540
+ "content": "ø̞",
541
+ "lstrip": true,
542
+ "normalized": false,
543
+ "rstrip": true,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "114": {
548
+ "content": "e̞",
549
+ "lstrip": true,
550
+ "normalized": false,
551
+ "rstrip": true,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "115": {
556
+ "content": "ä̃",
557
+ "lstrip": true,
558
+ "normalized": false,
559
+ "rstrip": true,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "118": {
564
+ "content": "d̼",
565
+ "lstrip": true,
566
+ "normalized": false,
567
+ "rstrip": true,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "119": {
572
+ "content": "õ",
573
+ "lstrip": true,
574
+ "normalized": false,
575
+ "rstrip": true,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "120": {
580
+ "content": "ɾ̥",
581
+ "lstrip": true,
582
+ "normalized": false,
583
+ "rstrip": true,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "123": {
588
+ "content": "ɢ̆",
589
+ "lstrip": true,
590
+ "normalized": false,
591
+ "rstrip": true,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "125": {
596
+ "content": "ã",
597
+ "lstrip": true,
598
+ "normalized": false,
599
+ "rstrip": true,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "126": {
604
+ "content": "qǁ",
605
+ "lstrip": true,
606
+ "normalized": false,
607
+ "rstrip": true,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "127": {
612
+ "content": "q͡ʡ",
613
+ "lstrip": true,
614
+ "normalized": false,
615
+ "rstrip": true,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "129": {
620
+ "content": "xʼ",
621
+ "lstrip": true,
622
+ "normalized": false,
623
+ "rstrip": true,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "131": {
628
+ "content": "ɡǂ",
629
+ "lstrip": true,
630
+ "normalized": false,
631
+ "rstrip": true,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "135": {
636
+ "content": "ɥ̊",
637
+ "lstrip": true,
638
+ "normalized": false,
639
+ "rstrip": true,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "140": {
644
+ "content": "t͡θ",
645
+ "lstrip": true,
646
+ "normalized": false,
647
+ "rstrip": true,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "144": {
652
+ "content": "ɳ̊",
653
+ "lstrip": true,
654
+ "normalized": false,
655
+ "rstrip": true,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "146": {
660
+ "content": "ɶ̃",
661
+ "lstrip": true,
662
+ "normalized": false,
663
+ "rstrip": true,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "147": {
668
+ "content": "ɴǃ",
669
+ "lstrip": true,
670
+ "normalized": false,
671
+ "rstrip": true,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "148": {
676
+ "content": "ʀ̥",
677
+ "lstrip": true,
678
+ "normalized": false,
679
+ "rstrip": true,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "149": {
684
+ "content": "p̚",
685
+ "lstrip": true,
686
+ "normalized": false,
687
+ "rstrip": true,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "152": {
692
+ "content": "ɡǃ",
693
+ "lstrip": true,
694
+ "normalized": false,
695
+ "rstrip": true,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "153": {
700
+ "content": "œ̃",
701
+ "lstrip": true,
702
+ "normalized": false,
703
+ "rstrip": true,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "155": {
708
+ "content": "ʄ̊",
709
+ "lstrip": true,
710
+ "normalized": false,
711
+ "rstrip": true,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "156": {
716
+ "content": "t͡s",
717
+ "lstrip": true,
718
+ "normalized": false,
719
+ "rstrip": true,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "158": {
724
+ "content": "ʌ̃",
725
+ "lstrip": true,
726
+ "normalized": false,
727
+ "rstrip": true,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "159": {
732
+ "content": "ʛ̥",
733
+ "lstrip": true,
734
+ "normalized": false,
735
+ "rstrip": true,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "161": {
740
+ "content": "ʟ̝̊",
741
+ "lstrip": true,
742
+ "normalized": false,
743
+ "rstrip": true,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "162": {
748
+ "content": "ɡʘ",
749
+ "lstrip": true,
750
+ "normalized": false,
751
+ "rstrip": true,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "164": {
756
+ "content": "t͡ɬʼ",
757
+ "lstrip": true,
758
+ "normalized": false,
759
+ "rstrip": true,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "167": {
764
+ "content": "ʙ̥",
765
+ "lstrip": true,
766
+ "normalized": false,
767
+ "rstrip": true,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "168": {
772
+ "content": "ŋʘ",
773
+ "lstrip": true,
774
+ "normalized": false,
775
+ "rstrip": true,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "169": {
780
+ "content": "n̼",
781
+ "lstrip": true,
782
+ "normalized": false,
783
+ "rstrip": true,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "170": {
788
+ "content": "t͡ɬ",
789
+ "lstrip": true,
790
+ "normalized": false,
791
+ "rstrip": true,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "172": {
796
+ "content": "m̥",
797
+ "lstrip": true,
798
+ "normalized": false,
799
+ "rstrip": true,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "173": {
804
+ "content": "ɹ̠̊˔",
805
+ "lstrip": true,
806
+ "normalized": false,
807
+ "rstrip": true,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "177": {
812
+ "content": "b̪",
813
+ "lstrip": true,
814
+ "normalized": false,
815
+ "rstrip": true,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "181": {
820
+ "content": "ɺ̥",
821
+ "lstrip": true,
822
+ "normalized": false,
823
+ "rstrip": true,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "183": {
828
+ "content": "tʼ",
829
+ "lstrip": true,
830
+ "normalized": false,
831
+ "rstrip": true,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "185": {
836
+ "content": "ɡ͡b",
837
+ "lstrip": true,
838
+ "normalized": false,
839
+ "rstrip": true,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "186": {
844
+ "content": "ɔ̃",
845
+ "lstrip": true,
846
+ "normalized": false,
847
+ "rstrip": true,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "187": {
852
+ "content": "ɤ̞",
853
+ "lstrip": true,
854
+ "normalized": false,
855
+ "rstrip": true,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "189": {
860
+ "content": "ɘ̃",
861
+ "lstrip": true,
862
+ "normalized": false,
863
+ "rstrip": true,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "190": {
868
+ "content": "ʈ͡ʂ",
869
+ "lstrip": true,
870
+ "normalized": false,
871
+ "rstrip": true,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "192": {
876
+ "content": "ð̠",
877
+ "lstrip": true,
878
+ "normalized": false,
879
+ "rstrip": true,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "193": {
884
+ "content": "ⱱ̟",
885
+ "lstrip": true,
886
+ "normalized": false,
887
+ "rstrip": true,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "197": {
892
+ "content": "ɲ̊",
893
+ "lstrip": true,
894
+ "normalized": false,
895
+ "rstrip": true,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "198": {
900
+ "content": "k͡x",
901
+ "lstrip": true,
902
+ "normalized": false,
903
+ "rstrip": true,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "200": {
908
+ "content": "sʼ",
909
+ "lstrip": true,
910
+ "normalized": false,
911
+ "rstrip": true,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "201": {
916
+ "content": "ɡ̆",
917
+ "lstrip": true,
918
+ "normalized": false,
919
+ "rstrip": true,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "202": {
924
+ "content": "ɹ̠˔",
925
+ "lstrip": true,
926
+ "normalized": false,
927
+ "rstrip": true,
928
+ "single_word": false,
929
+ "special": false
930
+ },
931
+ "203": {
932
+ "content": "ʔ͡h",
933
+ "lstrip": true,
934
+ "normalized": false,
935
+ "rstrip": true,
936
+ "single_word": false,
937
+ "special": false
938
+ },
939
+ "205": {
940
+ "content": "ʊ̃",
941
+ "lstrip": true,
942
+ "normalized": false,
943
+ "rstrip": true,
944
+ "single_word": false,
945
+ "special": false
946
+ },
947
+ "211": {
948
+ "content": "ẽ",
949
+ "lstrip": true,
950
+ "normalized": false,
951
+ "rstrip": true,
952
+ "single_word": false,
953
+ "special": false
954
+ },
955
+ "216": {
956
+ "content": "t̪͡θʼ",
957
+ "lstrip": true,
958
+ "normalized": false,
959
+ "rstrip": true,
960
+ "single_word": false,
961
+ "special": false
962
+ },
963
+ "217": {
964
+ "content": "æ̃",
965
+ "lstrip": true,
966
+ "normalized": false,
967
+ "rstrip": true,
968
+ "single_word": false,
969
+ "special": false
970
+ },
971
+ "218": {
972
+ "content": "ɽ̊",
973
+ "lstrip": true,
974
+ "normalized": false,
975
+ "rstrip": true,
976
+ "single_word": false,
977
+ "special": false
978
+ },
979
+ "221": {
980
+ "content": "ɴʘ",
981
+ "lstrip": true,
982
+ "normalized": false,
983
+ "rstrip": true,
984
+ "single_word": false,
985
+ "special": false
986
+ },
987
+ "225": {
988
+ "content": "p͡f",
989
+ "lstrip": true,
990
+ "normalized": false,
991
+ "rstrip": true,
992
+ "single_word": false,
993
+ "special": false
994
+ },
995
+ "226": {
996
+ "content": "ɡǁ",
997
+ "lstrip": true,
998
+ "normalized": false,
999
+ "rstrip": true,
1000
+ "single_word": false,
1001
+ "special": false
1002
+ },
1003
+ "227": {
1004
+ "content": "θ̼",
1005
+ "lstrip": true,
1006
+ "normalized": false,
1007
+ "rstrip": true,
1008
+ "single_word": false,
1009
+ "special": false
1010
+ },
1011
+ "229": {
1012
+ "content": "cʼ",
1013
+ "lstrip": true,
1014
+ "normalized": false,
1015
+ "rstrip": true,
1016
+ "single_word": false,
1017
+ "special": false
1018
+ },
1019
+ "230": {
1020
+ "content": "ʃʼ",
1021
+ "lstrip": true,
1022
+ "normalized": false,
1023
+ "rstrip": true,
1024
+ "single_word": false,
1025
+ "special": false
1026
+ },
1027
+ "231": {
1028
+ "content": "ŋǀ",
1029
+ "lstrip": true,
1030
+ "normalized": false,
1031
+ "rstrip": true,
1032
+ "single_word": false,
1033
+ "special": false
1034
+ },
1035
+ "234": {
1036
+ "content": "õ̞",
1037
+ "lstrip": true,
1038
+ "normalized": false,
1039
+ "rstrip": true,
1040
+ "single_word": false,
1041
+ "special": false
1042
+ },
1043
+ "236": {
1044
+ "content": "ɭ̆",
1045
+ "lstrip": true,
1046
+ "normalized": false,
1047
+ "rstrip": true,
1048
+ "single_word": false,
1049
+ "special": false
1050
+ },
1051
+ "237": {
1052
+ "content": "ʏ̃",
1053
+ "lstrip": true,
1054
+ "normalized": false,
1055
+ "rstrip": true,
1056
+ "single_word": false,
1057
+ "special": false
1058
+ },
1059
+ "238": {
1060
+ "content": "ɴǂ",
1061
+ "lstrip": true,
1062
+ "normalized": false,
1063
+ "rstrip": true,
1064
+ "single_word": false,
1065
+ "special": false
1066
+ },
1067
+ "240": {
1068
+ "content": "ɭ̥̆",
1069
+ "lstrip": true,
1070
+ "normalized": false,
1071
+ "rstrip": true,
1072
+ "single_word": false,
1073
+ "special": false
1074
+ },
1075
+ "241": {
1076
+ "content": "t̚",
1077
+ "lstrip": true,
1078
+ "normalized": false,
1079
+ "rstrip": true,
1080
+ "single_word": false,
1081
+ "special": false
1082
+ },
1083
+ "244": {
1084
+ "content": "d͡ð",
1085
+ "lstrip": true,
1086
+ "normalized": false,
1087
+ "rstrip": true,
1088
+ "single_word": false,
1089
+ "special": false
1090
+ },
1091
+ "248": {
1092
+ "content": "ʟ̆",
1093
+ "lstrip": true,
1094
+ "normalized": false,
1095
+ "rstrip": true,
1096
+ "single_word": false,
1097
+ "special": false
1098
+ },
1099
+ "249": {
1100
+ "content": "fʼ",
1101
+ "lstrip": true,
1102
+ "normalized": false,
1103
+ "rstrip": true,
1104
+ "single_word": false,
1105
+ "special": false
1106
+ },
1107
+ "250": {
1108
+ "content": "ʉ̃",
1109
+ "lstrip": true,
1110
+ "normalized": false,
1111
+ "rstrip": true,
1112
+ "single_word": false,
1113
+ "special": false
1114
+ },
1115
+ "255": {
1116
+ "content": "ʡ͡ʢ",
1117
+ "lstrip": true,
1118
+ "normalized": false,
1119
+ "rstrip": true,
1120
+ "single_word": false,
1121
+ "special": false
1122
+ },
1123
+ "257": {
1124
+ "content": "ʔ̞",
1125
+ "lstrip": true,
1126
+ "normalized": false,
1127
+ "rstrip": true,
1128
+ "single_word": false,
1129
+ "special": false
1130
+ },
1131
+ "258": {
1132
+ "content": "ɢǁ",
1133
+ "lstrip": true,
1134
+ "normalized": false,
1135
+ "rstrip": true,
1136
+ "single_word": false,
1137
+ "special": false
1138
+ },
1139
+ "260": {
1140
+ "content": "χʼ",
1141
+ "lstrip": true,
1142
+ "normalized": false,
1143
+ "rstrip": true,
1144
+ "single_word": false,
1145
+ "special": false
1146
+ },
1147
+ "261": {
1148
+ "content": "qʘ",
1149
+ "lstrip": true,
1150
+ "normalized": false,
1151
+ "rstrip": true,
1152
+ "single_word": false,
1153
+ "special": false
1154
+ },
1155
+ "262": {
1156
+ "content": "ʎ̝",
1157
+ "lstrip": true,
1158
+ "normalized": false,
1159
+ "rstrip": true,
1160
+ "single_word": false,
1161
+ "special": false
1162
+ },
1163
+ "263": {
1164
+ "content": "d͡z",
1165
+ "lstrip": true,
1166
+ "normalized": false,
1167
+ "rstrip": true,
1168
+ "single_word": false,
1169
+ "special": false
1170
+ },
1171
+ "264": {
1172
+ "content": "t͡ɕ",
1173
+ "lstrip": true,
1174
+ "normalized": false,
1175
+ "rstrip": true,
1176
+ "single_word": false,
1177
+ "special": false
1178
+ },
1179
+ "265": {
1180
+ "content": "ẽ̞",
1181
+ "lstrip": true,
1182
+ "normalized": false,
1183
+ "rstrip": true,
1184
+ "single_word": false,
1185
+ "special": false
1186
+ },
1187
+ "268": {
1188
+ "content": "ᶑ̊",
1189
+ "lstrip": true,
1190
+ "normalized": false,
1191
+ "rstrip": true,
1192
+ "single_word": false,
1193
+ "special": false
1194
+ },
1195
+ "270": {
1196
+ "content": "ɗ̥",
1197
+ "lstrip": true,
1198
+ "normalized": false,
1199
+ "rstrip": true,
1200
+ "single_word": false,
1201
+ "special": false
1202
+ },
1203
+ "273": {
1204
+ "content": "p̪",
1205
+ "lstrip": true,
1206
+ "normalized": false,
1207
+ "rstrip": true,
1208
+ "single_word": false,
1209
+ "special": false
1210
+ },
1211
+ "277": {
1212
+ "content": "ỹ",
1213
+ "lstrip": true,
1214
+ "normalized": false,
1215
+ "rstrip": true,
1216
+ "single_word": false,
1217
+ "special": false
1218
+ },
1219
+ "279": {
1220
+ "content": "ɭ˔",
1221
+ "lstrip": true,
1222
+ "normalized": false,
1223
+ "rstrip": true,
1224
+ "single_word": false,
1225
+ "special": false
1226
+ },
1227
+ "280": {
1228
+ "content": "d͡ʒ",
1229
+ "lstrip": true,
1230
+ "normalized": false,
1231
+ "rstrip": true,
1232
+ "single_word": false,
1233
+ "special": false
1234
+ },
1235
+ "281": {
1236
+ "content": "kxʼ",
1237
+ "lstrip": true,
1238
+ "normalized": false,
1239
+ "rstrip": true,
1240
+ "single_word": false,
1241
+ "special": false
1242
+ },
1243
+ "284": {
1244
+ "content": "ŋǃ",
1245
+ "lstrip": true,
1246
+ "normalized": false,
1247
+ "rstrip": true,
1248
+ "single_word": false,
1249
+ "special": false
1250
+ },
1251
+ "285": {
1252
+ "content": "ʟ̠",
1253
+ "lstrip": true,
1254
+ "normalized": false,
1255
+ "rstrip": true,
1256
+ "single_word": false,
1257
+ "special": false
1258
+ },
1259
+ "286": {
1260
+ "content": "pʼ",
1261
+ "lstrip": true,
1262
+ "normalized": false,
1263
+ "rstrip": true,
1264
+ "single_word": false,
1265
+ "special": false
1266
+ },
1267
+ "287": {
1268
+ "content": "b͡ꞵ",
1269
+ "lstrip": true,
1270
+ "normalized": false,
1271
+ "rstrip": true,
1272
+ "single_word": false,
1273
+ "special": false
1274
+ },
1275
+ "289": {
1276
+ "content": "b̪͡v",
1277
+ "lstrip": true,
1278
+ "normalized": false,
1279
+ "rstrip": true,
1280
+ "single_word": false,
1281
+ "special": false
1282
+ },
1283
+ "291": {
1284
+ "content": "q͡χʼ",
1285
+ "lstrip": true,
1286
+ "normalized": false,
1287
+ "rstrip": true,
1288
+ "single_word": false,
1289
+ "special": false
1290
+ },
1291
+ "294": {
1292
+ "content": "ə̃",
1293
+ "lstrip": true,
1294
+ "normalized": false,
1295
+ "rstrip": true,
1296
+ "single_word": false,
1297
+ "special": false
1298
+ },
1299
+ "296": {
1300
+ "content": "ŋ͡m",
1301
+ "lstrip": true,
1302
+ "normalized": false,
1303
+ "rstrip": true,
1304
+ "single_word": false,
1305
+ "special": false
1306
+ },
1307
+ "299": {
1308
+ "content": "qǂ",
1309
+ "lstrip": true,
1310
+ "normalized": false,
1311
+ "rstrip": true,
1312
+ "single_word": false,
1313
+ "special": false
1314
+ },
1315
+ "300": {
1316
+ "content": "ɯ̃",
1317
+ "lstrip": true,
1318
+ "normalized": false,
1319
+ "rstrip": true,
1320
+ "single_word": false,
1321
+ "special": false
1322
+ },
1323
+ "301": {
1324
+ "content": "ŋǂ",
1325
+ "lstrip": true,
1326
+ "normalized": false,
1327
+ "rstrip": true,
1328
+ "single_word": false,
1329
+ "special": false
1330
+ },
1331
+ "302": {
1332
+ "content": "qǀ",
1333
+ "lstrip": true,
1334
+ "normalized": false,
1335
+ "rstrip": true,
1336
+ "single_word": false,
1337
+ "special": false
1338
+ },
1339
+ "304": {
1340
+ "content": "ŋǁ",
1341
+ "lstrip": true,
1342
+ "normalized": false,
1343
+ "rstrip": true,
1344
+ "single_word": false,
1345
+ "special": false
1346
+ },
1347
+ "306": {
1348
+ "content": "ɸʼ",
1349
+ "lstrip": true,
1350
+ "normalized": false,
1351
+ "rstrip": true,
1352
+ "single_word": false,
1353
+ "special": false
1354
+ },
1355
+ "308": {
1356
+ "content": "ɢǃ",
1357
+ "lstrip": true,
1358
+ "normalized": false,
1359
+ "rstrip": true,
1360
+ "single_word": false,
1361
+ "special": false
1362
+ },
1363
+ "309": {
1364
+ "content": "[UNK]",
1365
+ "lstrip": true,
1366
+ "normalized": false,
1367
+ "rstrip": true,
1368
+ "single_word": false,
1369
+ "special": false
1370
+ },
1371
+ "310": {
1372
+ "content": "[PAD]",
1373
+ "lstrip": true,
1374
+ "normalized": false,
1375
+ "rstrip": true,
1376
+ "single_word": false,
1377
+ "special": false
1378
+ },
1379
+ "311": {
1380
+ "content": "<s>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "312": {
1388
+ "content": "</s>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ }
1395
+ },
1396
+ "bos_token": "<s>",
1397
+ "clean_up_tokenization_spaces": true,
1398
+ "do_lower_case": false,
1399
+ "eos_token": "</s>",
1400
+ "model_max_length": 1000000000000000019884624838656,
1401
+ "pad_token": "[PAD]",
1402
+ "processor_class": "Wav2Vec2Processor",
1403
+ "replace_word_delimiter_char": " ",
1404
+ "target_lang": null,
1405
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
1406
+ "unk_token": "[UNK]",
1407
+ "word_delimiter_token": "|"
1408
+ }
vocab.json ADDED
@@ -0,0 +1,313 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "A": 267,
3
+ "E": 45,
4
+ "H": 72,
5
+ "I": 20,
6
+ "O": 305,
7
+ "U": 292,
8
+ "[PAD]": 310,
9
+ "[UNK]": 309,
10
+ "_": 182,
11
+ "a": 53,
12
+ "ã": 125,
13
+ "b": 113,
14
+ "b̪": 177,
15
+ "b̪͡v": 289,
16
+ "b͡ꞵ": 287,
17
+ "c": 25,
18
+ "cʼ": 229,
19
+ "c͡ç": 66,
20
+ "d": 176,
21
+ "d̼": 118,
22
+ "d͡z": 263,
23
+ "d͡ð": 244,
24
+ "d͡ɮ": 18,
25
+ "d͡ʑ": 94,
26
+ "d͡ʒ": 280,
27
+ "e": 175,
28
+ "ẽ": 211,
29
+ "e̞": 114,
30
+ "ẽ̞": 265,
31
+ "f": 139,
32
+ "fʼ": 249,
33
+ "h": 179,
34
+ "i": 245,
35
+ "j": 215,
36
+ "k": 282,
37
+ "kxʼ": 281,
38
+ "kǀ": 41,
39
+ "kǁ": 61,
40
+ "kǂ": 21,
41
+ "kǃ": 70,
42
+ "kʘ": 79,
43
+ "kʼ": 39,
44
+ "k̚": 89,
45
+ "k͡p": 48,
46
+ "k͡x": 198,
47
+ "l": 303,
48
+ "m": 75,
49
+ "m̥": 172,
50
+ "n": 102,
51
+ "n̥": 28,
52
+ "n̼": 169,
53
+ "o": 117,
54
+ "õ": 119,
55
+ "o̞": 62,
56
+ "õ̞": 234,
57
+ "p": 259,
58
+ "pʼ": 286,
59
+ "p̚": 149,
60
+ "p̪": 273,
61
+ "p̪͡f": 105,
62
+ "p͡f": 225,
63
+ "p͡ɸ": 103,
64
+ "q": 130,
65
+ "qǀ": 302,
66
+ "qǁ": 126,
67
+ "qǂ": 299,
68
+ "qǃ": 37,
69
+ "qʘ": 261,
70
+ "qʼ": 58,
71
+ "q͡ʡ": 127,
72
+ "q͡χʼ": 291,
73
+ "q͡ꭓ": 4,
74
+ "r": 82,
75
+ "r̥": 34,
76
+ "s": 247,
77
+ "sʼ": 200,
78
+ "t": 307,
79
+ "tʼ": 183,
80
+ "t̚": 241,
81
+ "t̪͡θʼ": 216,
82
+ "t̼": 87,
83
+ "t͡s": 156,
84
+ "t͡sʼ": 43,
85
+ "t͡ɕ": 264,
86
+ "t͡ɬ": 170,
87
+ "t͡ɬʼ": 164,
88
+ "t͡ʃ": 91,
89
+ "t͡ʃʼ": 108,
90
+ "t͡θ": 140,
91
+ "u": 154,
92
+ "ũ": 81,
93
+ "v": 243,
94
+ "w": 143,
95
+ "x": 133,
96
+ "xʼ": 129,
97
+ "y": 214,
98
+ "ỹ": 277,
99
+ "z": 271,
100
+ "{": 251,
101
+ "}": 74,
102
+ "ã": 99,
103
+ "ä": 165,
104
+ "ä̃": 115,
105
+ "æ": 191,
106
+ "æ̃": 217,
107
+ "ç": 71,
108
+ "ð": 69,
109
+ "ð̠": 192,
110
+ "ð̼": 9,
111
+ "õ": 157,
112
+ "ø": 47,
113
+ "ø̃": 46,
114
+ "ø̞": 112,
115
+ "ø̞̃": 12,
116
+ "ħ": 224,
117
+ "ĩ": 180,
118
+ "ŋ": 213,
119
+ "ŋǀ": 231,
120
+ "ŋǁ": 304,
121
+ "ŋǂ": 301,
122
+ "ŋǃ": 284,
123
+ "ŋʘ": 168,
124
+ "ŋ̊": 27,
125
+ "ŋ͡m": 296,
126
+ "œ": 29,
127
+ "œ̃": 153,
128
+ "ũ": 31,
129
+ "ɐ": 142,
130
+ "ɐ̃": 7,
131
+ "ɑ": 49,
132
+ "ɑ̃": 50,
133
+ "ɒ": 116,
134
+ "ɒ̃": 85,
135
+ "ɓ": 178,
136
+ "ɓ̥": 13,
137
+ "ɔ": 228,
138
+ "ɔ̃": 186,
139
+ "ɕ": 220,
140
+ "ɕʼ": 36,
141
+ "ɖ": 256,
142
+ "ɖ͡ʐ": 77,
143
+ "ɗ": 93,
144
+ "ɗ̥": 270,
145
+ "ɘ": 104,
146
+ "ɘ̃": 189,
147
+ "ə": 6,
148
+ "ə̃": 294,
149
+ "ɚ": 184,
150
+ "ɛ": 293,
151
+ "ɛ̃": 98,
152
+ "ɜ": 92,
153
+ "ɜ̃": 73,
154
+ "ɝ": 196,
155
+ "ɞ": 210,
156
+ "ɞ̃": 54,
157
+ "ɟ": 68,
158
+ "ɟ͡ʝ": 86,
159
+ "ɠ": 160,
160
+ "ɠ̊": 1,
161
+ "ɡ": 252,
162
+ "ɡǀ": 19,
163
+ "ɡǁ": 226,
164
+ "ɡǂ": 131,
165
+ "ɡǃ": 152,
166
+ "ɡʘ": 162,
167
+ "ɡ̆": 201,
168
+ "ɡ͡b": 185,
169
+ "ɡ͡ɣ": 78,
170
+ "ɢ": 195,
171
+ "ɢǀ": 88,
172
+ "ɢǁ": 258,
173
+ "ɢǂ": 64,
174
+ "ɢǃ": 308,
175
+ "ɢʘ": 107,
176
+ "ɢ̆": 123,
177
+ "ɢ͡ʁ": 111,
178
+ "ɣ": 219,
179
+ "ɤ": 194,
180
+ "ɤ̃": 17,
181
+ "ɤ̞": 187,
182
+ "ɤ̞̃": 60,
183
+ "ɥ": 24,
184
+ "ɥ̊": 135,
185
+ "ɧ": 246,
186
+ "ɨ": 40,
187
+ "ɨ̃": 109,
188
+ "ɪ": 8,
189
+ "ɪ̃": 97,
190
+ "ɬ": 121,
191
+ "ɬʼ": 3,
192
+ "ɭ": 290,
193
+ "ɭ˔": 279,
194
+ "ɭ̆": 236,
195
+ "ɭ̥̆": 240,
196
+ "ɮ": 266,
197
+ "ɯ": 275,
198
+ "ɯ̃": 300,
199
+ "ɰ": 208,
200
+ "ɱ": 295,
201
+ "ɲ": 128,
202
+ "ɲ̊": 197,
203
+ "ɳ": 63,
204
+ "ɳ̊": 144,
205
+ "ɴ": 136,
206
+ "ɴǀ": 101,
207
+ "ɴǁ": 14,
208
+ "ɴǂ": 238,
209
+ "ɴǃ": 147,
210
+ "ɴʘ": 221,
211
+ "ɵ": 95,
212
+ "ɵ̃": 51,
213
+ "ɶ": 145,
214
+ "ɶ̃": 146,
215
+ "ɸ": 166,
216
+ "ɸʼ": 306,
217
+ "ɹ": 223,
218
+ "ɹ̠˔": 202,
219
+ "ɹ̠̊˔": 173,
220
+ "ɺ": 76,
221
+ "ɺ̥": 181,
222
+ "ɻ": 163,
223
+ "ɻ˔": 30,
224
+ "ɻ̊˔": 42,
225
+ "ɽ": 254,
226
+ "ɽ̊": 218,
227
+ "ɾ": 232,
228
+ "ɾ̥": 120,
229
+ "ɾ̼": 32,
230
+ "ʀ": 52,
231
+ "ʀ̥": 148,
232
+ "ʁ": 239,
233
+ "ʂ": 242,
234
+ "ʂʼ": 110,
235
+ "ʃ": 253,
236
+ "ʃʼ": 230,
237
+ "ʄ": 132,
238
+ "ʄ̊": 155,
239
+ "ʈ": 199,
240
+ "ʈʼ": 44,
241
+ "ʈ͡ʂ": 190,
242
+ "ʈ͡ʂʼ": 67,
243
+ "ʉ": 80,
244
+ "ʉ̃": 250,
245
+ "ʊ": 83,
246
+ "ʊ̃": 205,
247
+ "ʋ": 106,
248
+ "ʌ": 272,
249
+ "ʌ̃": 158,
250
+ "ʍ": 141,
251
+ "ʎ": 276,
252
+ "ʎ̆": 84,
253
+ "ʎ̝": 262,
254
+ "ʎ̝̊": 59,
255
+ "ʏ": 23,
256
+ "ʏ̃": 237,
257
+ "ʐ": 209,
258
+ "ʑ": 137,
259
+ "ʒ": 171,
260
+ "ʔ": 10,
261
+ "ʔ̞": 257,
262
+ "ʔ͡h": 203,
263
+ "ʕ": 38,
264
+ "ʙ": 274,
265
+ "ʙ̥": 167,
266
+ "ʛ": 233,
267
+ "ʛ̥": 159,
268
+ "ʜ": 298,
269
+ "ʝ": 35,
270
+ "ʟ": 150,
271
+ "ʟ̆": 248,
272
+ "ʟ̝": 33,
273
+ "ʟ̝̊": 161,
274
+ "ʟ̠": 285,
275
+ "ʡ": 174,
276
+ "ʡʼ": 5,
277
+ "ʡ̆": 22,
278
+ "ʡ͡ʜ": 56,
279
+ "ʡ͡ʢ": 255,
280
+ "ʢ": 188,
281
+ "ʰ": 206,
282
+ "ʲ": 0,
283
+ "ʷ": 288,
284
+ "ː": 235,
285
+ "˞": 90,
286
+ "ˠ": 122,
287
+ "ˡ": 16,
288
+ "ˣ": 96,
289
+ "ˤ": 15,
290
+ "̃": 57,
291
+ "̩": 204,
292
+ "β": 269,
293
+ "θ": 283,
294
+ "θʼ": 26,
295
+ "θ̠": 100,
296
+ "θ̼": 227,
297
+ "χ": 65,
298
+ "χʼ": 260,
299
+ "ᵐ": 124,
300
+ "ᵑ": 297,
301
+ "ᶑ": 212,
302
+ "ᶑ̊": 268,
303
+ "ᶬ": 151,
304
+ "ᶮ": 55,
305
+ "ᶯ": 207,
306
+ "ᶰ": 11,
307
+ "ᶿ": 138,
308
+ "ẽ": 2,
309
+ "ⁿ": 222,
310
+ "ⱱ": 134,
311
+ "ⱱ̟": 193,
312
+ "ꞎ": 278
313
+ }