jonatasgrosman commited on
Commit
1a0db30
1 Parent(s): 3ebe1c5

jonatasgrosman/exp_w2v2r_fr_vp-100k_age_teens-0_sixties-10_s131

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ cv7_transcriptions.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - fr
4
+ license: apache-2.0
5
+ tags:
6
+ - automatic-speech-recognition
7
+ - fr
8
+ datasets:
9
+ - mozilla-foundation/common_voice_7_0
10
+ ---
11
+ # exp_w2v2r_fr_vp-100k_age_teens-0_sixties-10_s131
12
+
13
+ Fine-tuned [facebook/wav2vec2-large-100k-voxpopuli](https://huggingface.co/facebook/wav2vec2-large-100k-voxpopuli) for speech recognition using the train split of [Common Voice 7.0 (fr)](https://huggingface.co/datasets/mozilla-foundation/common_voice_7_0).
14
+ When using this model, make sure that your speech input is sampled at 16kHz.
15
+
16
+ This model has been fine-tuned by the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) tool.
17
+
config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-100k-voxpopuli",
3
+ "activation_dropout": 0.05,
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": 0.05,
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
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.05,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.05,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1024,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 4096,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.05,
63
+ "mask_channel_length": 10,
64
+ "mask_channel_min_space": 1,
65
+ "mask_channel_other": 0.0,
66
+ "mask_channel_prob": 0.0,
67
+ "mask_channel_selection": "static",
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_min_space": 1,
74
+ "mask_time_other": 0.0,
75
+ "mask_time_prob": 0.05,
76
+ "mask_time_selection": "static",
77
+ "model_type": "wav2vec2",
78
+ "num_adapter_layers": 3,
79
+ "num_attention_heads": 16,
80
+ "num_codevector_groups": 2,
81
+ "num_codevectors_per_group": 320,
82
+ "num_conv_pos_embedding_groups": 16,
83
+ "num_conv_pos_embeddings": 128,
84
+ "num_feat_extract_layers": 7,
85
+ "num_hidden_layers": 24,
86
+ "num_negatives": 100,
87
+ "output_hidden_size": 1024,
88
+ "pad_token_id": 0,
89
+ "proj_codevector_dim": 768,
90
+ "tdnn_dilation": [
91
+ 1,
92
+ 2,
93
+ 3,
94
+ 1,
95
+ 1
96
+ ],
97
+ "tdnn_dim": [
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 1500
103
+ ],
104
+ "tdnn_kernel": [
105
+ 5,
106
+ 3,
107
+ 3,
108
+ 1,
109
+ 1
110
+ ],
111
+ "torch_dtype": "float32",
112
+ "transformers_version": "4.18.0",
113
+ "use_weighted_layer_sum": false,
114
+ "vocab_size": 57,
115
+ "xvector_output_dim": 512
116
+ }
cv7_evaluation.json ADDED
@@ -0,0 +1,444 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "validation": [
3
+ {
4
+ "subset_type": "all",
5
+ "subset": "all",
6
+ "cer": 0.1059054403581409,
7
+ "wer": 0.34772107170013866
8
+ },
9
+ {
10
+ "subset_type": "age",
11
+ "subset": "",
12
+ "cer": 0.10335042783659086,
13
+ "wer": 0.34161427702291625
14
+ },
15
+ {
16
+ "subset_type": "age",
17
+ "subset": "seventies",
18
+ "cer": 0.10576769451989136,
19
+ "wer": 0.35344827586206895
20
+ },
21
+ {
22
+ "subset_type": "age",
23
+ "subset": "sixties",
24
+ "cer": 0.09455587392550144,
25
+ "wer": 0.331763698630137
26
+ },
27
+ {
28
+ "subset_type": "age",
29
+ "subset": "thirties",
30
+ "cer": 0.11879446384685034,
31
+ "wer": 0.37707948243992606
32
+ },
33
+ {
34
+ "subset_type": "age",
35
+ "subset": "eighties",
36
+ "cer": 0.09142857142857143,
37
+ "wer": 0.3448275862068966
38
+ },
39
+ {
40
+ "subset_type": "age",
41
+ "subset": "twenties",
42
+ "cer": 0.12104828279925277,
43
+ "wer": 0.3851084285866895
44
+ },
45
+ {
46
+ "subset_type": "age",
47
+ "subset": "fourties",
48
+ "cer": 0.12002494834912096,
49
+ "wer": 0.3813500347947112
50
+ },
51
+ {
52
+ "subset_type": "age",
53
+ "subset": "fifties",
54
+ "cer": 0.1186187432555823,
55
+ "wer": 0.36390977443609024
56
+ },
57
+ {
58
+ "subset_type": "age",
59
+ "subset": "teens",
60
+ "cer": 0.12388266398086366,
61
+ "wer": 0.38311926605504587
62
+ },
63
+ {
64
+ "subset_type": "gender",
65
+ "subset": "",
66
+ "cer": 0.10334979672748043,
67
+ "wer": 0.3416058507984032
68
+ },
69
+ {
70
+ "subset_type": "gender",
71
+ "subset": "other",
72
+ "cer": 0.10932323710364411,
73
+ "wer": 0.3439306358381503
74
+ },
75
+ {
76
+ "subset_type": "gender",
77
+ "subset": "female",
78
+ "cer": 0.12671613016299585,
79
+ "wer": 0.3939393939393939
80
+ },
81
+ {
82
+ "subset_type": "gender",
83
+ "subset": "male",
84
+ "cer": 0.11543472661990395,
85
+ "wer": 0.371270419873093
86
+ },
87
+ {
88
+ "subset_type": "accent",
89
+ "subset": "",
90
+ "cer": 0.10445376952131039,
91
+ "wer": 0.34432658407133554
92
+ },
93
+ {
94
+ "subset_type": "accent",
95
+ "subset": "italy",
96
+ "cer": 0.23789473684210527,
97
+ "wer": 0.569620253164557
98
+ },
99
+ {
100
+ "subset_type": "accent",
101
+ "subset": "united_states",
102
+ "cer": 0.13975155279503104,
103
+ "wer": 0.38769230769230767
104
+ },
105
+ {
106
+ "subset_type": "accent",
107
+ "subset": "germany",
108
+ "cer": 0.09563758389261745,
109
+ "wer": 0.36792452830188677
110
+ },
111
+ {
112
+ "subset_type": "accent",
113
+ "subset": "gabon",
114
+ "cer": 0.13333333333333333,
115
+ "wer": 0.4375
116
+ },
117
+ {
118
+ "subset_type": "accent",
119
+ "subset": "martinique",
120
+ "cer": 0.1532258064516129,
121
+ "wer": 0.42105263157894735
122
+ },
123
+ {
124
+ "subset_type": "accent",
125
+ "subset": "belgium",
126
+ "cer": 0.11711452794941803,
127
+ "wer": 0.36050420168067226
128
+ },
129
+ {
130
+ "subset_type": "accent",
131
+ "subset": "monaco",
132
+ "cer": 0.04644808743169399,
133
+ "wer": 0.25396825396825395
134
+ },
135
+ {
136
+ "subset_type": "accent",
137
+ "subset": "algeria",
138
+ "cer": 0.15879828326180256,
139
+ "wer": 0.488
140
+ },
141
+ {
142
+ "subset_type": "accent",
143
+ "subset": "st_pierre_et_miquelon",
144
+ "cer": 0.3310104529616725,
145
+ "wer": 0.7708333333333334
146
+ },
147
+ {
148
+ "subset_type": "accent",
149
+ "subset": "france",
150
+ "cer": 0.10676596393518928,
151
+ "wer": 0.35226780818623443
152
+ },
153
+ {
154
+ "subset_type": "accent",
155
+ "subset": "guadeloupe",
156
+ "cer": 0.09540636042402827,
157
+ "wer": 0.3263888888888889
158
+ },
159
+ {
160
+ "subset_type": "accent",
161
+ "subset": "canada",
162
+ "cer": 0.16609362602486114,
163
+ "wer": 0.48236196319018404
164
+ },
165
+ {
166
+ "subset_type": "accent",
167
+ "subset": "cameroon",
168
+ "cer": 0.26666666666666666,
169
+ "wer": 0.6265060240963856
170
+ },
171
+ {
172
+ "subset_type": "accent",
173
+ "subset": "luxembourg",
174
+ "cer": 0.14736842105263157,
175
+ "wer": 0.48333333333333334
176
+ },
177
+ {
178
+ "subset_type": "accent",
179
+ "subset": "tunisia",
180
+ "cer": 0.2533783783783784,
181
+ "wer": 0.5416666666666666
182
+ },
183
+ {
184
+ "subset_type": "accent",
185
+ "subset": "switzerland",
186
+ "cer": 0.09073987901349465,
187
+ "wer": 0.30193905817174516
188
+ },
189
+ {
190
+ "subset_type": "accent",
191
+ "subset": "romania",
192
+ "cer": 0.17054263565891473,
193
+ "wer": 0.5777777777777777
194
+ },
195
+ {
196
+ "subset_type": "accent",
197
+ "subset": "united_kingdom",
198
+ "cer": 0.16605166051660517,
199
+ "wer": 0.6521739130434783
200
+ },
201
+ {
202
+ "subset_type": "accent",
203
+ "subset": "mayotte",
204
+ "cer": 0.02575107296137339,
205
+ "wer": 0.13157894736842105
206
+ },
207
+ {
208
+ "subset_type": "accent",
209
+ "subset": "senegal",
210
+ "cer": 0.20279720279720279,
211
+ "wer": 0.52
212
+ },
213
+ {
214
+ "subset_type": "accent",
215
+ "subset": "cote_d_ivoire",
216
+ "cer": 0.311787072243346,
217
+ "wer": 0.7121212121212122
218
+ },
219
+ {
220
+ "subset_type": "accent",
221
+ "subset": "morocco",
222
+ "cer": 0.06020066889632107,
223
+ "wer": 0.25
224
+ }
225
+ ],
226
+ "test": [
227
+ {
228
+ "subset_type": "all",
229
+ "subset": "all",
230
+ "cer": 0.12009659943867894,
231
+ "wer": 0.36980371527623734
232
+ },
233
+ {
234
+ "subset_type": "age",
235
+ "subset": "",
236
+ "cer": 0.11869471554796952,
237
+ "wer": 0.3660326504903433
238
+ },
239
+ {
240
+ "subset_type": "age",
241
+ "subset": "seventies",
242
+ "cer": 0.1109229466553768,
243
+ "wer": 0.3610169491525424
244
+ },
245
+ {
246
+ "subset_type": "age",
247
+ "subset": "sixties",
248
+ "cer": 0.12108369910700773,
249
+ "wer": 0.3707916287534122
250
+ },
251
+ {
252
+ "subset_type": "age",
253
+ "subset": "thirties",
254
+ "cer": 0.13430881091089736,
255
+ "wer": 0.4034896401308615
256
+ },
257
+ {
258
+ "subset_type": "age",
259
+ "subset": "twenties",
260
+ "cer": 0.13596350465361515,
261
+ "wer": 0.41550260202684197
262
+ },
263
+ {
264
+ "subset_type": "age",
265
+ "subset": "fourties",
266
+ "cer": 0.12827725891751998,
267
+ "wer": 0.384946949602122
268
+ },
269
+ {
270
+ "subset_type": "age",
271
+ "subset": "fifties",
272
+ "cer": 0.11076134699853588,
273
+ "wer": 0.35275938189845474
274
+ },
275
+ {
276
+ "subset_type": "age",
277
+ "subset": "teens",
278
+ "cer": 0.1311463159467942,
279
+ "wer": 0.3941043083900227
280
+ },
281
+ {
282
+ "subset_type": "gender",
283
+ "subset": "female",
284
+ "cer": 0.1297291118985027,
285
+ "wer": 0.4076799264198666
286
+ },
287
+ {
288
+ "subset_type": "gender",
289
+ "subset": "",
290
+ "cer": 0.11863762455122694,
291
+ "wer": 0.3659791174297024
292
+ },
293
+ {
294
+ "subset_type": "gender",
295
+ "subset": "other",
296
+ "cer": 0.20892594409024032,
297
+ "wer": 0.5029411764705882
298
+ },
299
+ {
300
+ "subset_type": "gender",
301
+ "subset": "male",
302
+ "cer": 0.12790555668634235,
303
+ "wer": 0.38884491262254156
304
+ },
305
+ {
306
+ "subset_type": "accent",
307
+ "subset": "",
308
+ "cer": 0.11961135507561849,
309
+ "wer": 0.36856503711725064
310
+ },
311
+ {
312
+ "subset_type": "accent",
313
+ "subset": "reunion",
314
+ "cer": 0.13166144200626959,
315
+ "wer": 0.42592592592592593
316
+ },
317
+ {
318
+ "subset_type": "accent",
319
+ "subset": "united_states",
320
+ "cer": 0.25598219254312743,
321
+ "wer": 0.6153846153846154
322
+ },
323
+ {
324
+ "subset_type": "accent",
325
+ "subset": "other",
326
+ "cer": 0.04672897196261682,
327
+ "wer": 0.15
328
+ },
329
+ {
330
+ "subset_type": "accent",
331
+ "subset": "germany",
332
+ "cer": 0.1421832884097035,
333
+ "wer": 0.44534412955465585
334
+ },
335
+ {
336
+ "subset_type": "accent",
337
+ "subset": "martinique",
338
+ "cer": 0.11403508771929824,
339
+ "wer": 0.2631578947368421
340
+ },
341
+ {
342
+ "subset_type": "accent",
343
+ "subset": "belgium",
344
+ "cer": 0.10553158101216163,
345
+ "wer": 0.34965034965034963
346
+ },
347
+ {
348
+ "subset_type": "accent",
349
+ "subset": "algeria",
350
+ "cer": 0.12926391382405744,
351
+ "wer": 0.3978494623655914
352
+ },
353
+ {
354
+ "subset_type": "accent",
355
+ "subset": "monaco",
356
+ "cer": 0.1276595744680851,
357
+ "wer": 0.37735849056603776
358
+ },
359
+ {
360
+ "subset_type": "accent",
361
+ "subset": "burundi",
362
+ "cer": 0.17857142857142858,
363
+ "wer": 0.7142857142857143
364
+ },
365
+ {
366
+ "subset_type": "accent",
367
+ "subset": "france",
368
+ "cer": 0.11605406336935917,
369
+ "wer": 0.3639127855235835
370
+ },
371
+ {
372
+ "subset_type": "accent",
373
+ "subset": "guadeloupe",
374
+ "cer": 0.03162055335968379,
375
+ "wer": 0.19047619047619047
376
+ },
377
+ {
378
+ "subset_type": "accent",
379
+ "subset": "canada",
380
+ "cer": 0.18367056141350813,
381
+ "wer": 0.49745762711864405
382
+ },
383
+ {
384
+ "subset_type": "accent",
385
+ "subset": "cameroon",
386
+ "cer": 0.18888888888888888,
387
+ "wer": 0.45454545454545453
388
+ },
389
+ {
390
+ "subset_type": "accent",
391
+ "subset": "new_caledonia",
392
+ "cer": 0.2140221402214022,
393
+ "wer": 0.43902439024390244
394
+ },
395
+ {
396
+ "subset_type": "accent",
397
+ "subset": "tunisia",
398
+ "cer": 0.1596330275229358,
399
+ "wer": 0.4574468085106383
400
+ },
401
+ {
402
+ "subset_type": "accent",
403
+ "subset": "switzerland",
404
+ "cer": 0.11526670754138565,
405
+ "wer": 0.3722627737226277
406
+ },
407
+ {
408
+ "subset_type": "accent",
409
+ "subset": "benin",
410
+ "cer": 0.09545454545454546,
411
+ "wer": 0.34210526315789475
412
+ },
413
+ {
414
+ "subset_type": "accent",
415
+ "subset": "romania",
416
+ "cer": 0.13740458015267176,
417
+ "wer": 0.45454545454545453
418
+ },
419
+ {
420
+ "subset_type": "accent",
421
+ "subset": "united_kingdom",
422
+ "cer": 0.22857142857142856,
423
+ "wer": 0.5555555555555556
424
+ },
425
+ {
426
+ "subset_type": "accent",
427
+ "subset": "senegal",
428
+ "cer": 0.10574018126888217,
429
+ "wer": 0.3274336283185841
430
+ },
431
+ {
432
+ "subset_type": "accent",
433
+ "subset": "cote_d_ivoire",
434
+ "cer": 0.19362186788154898,
435
+ "wer": 0.5104895104895105
436
+ },
437
+ {
438
+ "subset_type": "accent",
439
+ "subset": "morocco",
440
+ "cer": 0.08403361344537816,
441
+ "wer": 0.29310344827586204
442
+ }
443
+ ]
444
+ }
cv7_transcriptions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c55a7b750a62b1774979492ff2156b0f34bee29f3074293b238c15733f1330f
3
+ size 129036845
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c76d076c5c51bf9c1db8c6aff7b7fc68797f6f38e151b3bbdc815e8972b1060d
3
+ size 1262132401
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "/tmp/tmpnd9uwqfq", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "'": 5, "-": 6, "a": 7, "b": 8, "c": 9, "d": 10, "e": 11, "f": 12, "g": 13, "h": 14, "i": 15, "j": 16, "k": 17, "l": 18, "m": 19, "n": 20, "o": 21, "p": 22, "q": 23, "r": 24, "s": 25, "t": 26, "u": 27, "v": 28, "w": 29, "x": 30, "y": 31, "z": 32, "à": 33, "á": 34, "â": 35, "ä": 36, "ç": 37, "è": 38, "é": 39, "ê": 40, "ë": 41, "í": 42, "î": 43, "ï": 44, "ó": 45, "ô": 46, "ö": 47, "ù": 48, "û": 49, "ü": 50, "ć": 51, "č": 52, "ł": 53, "ō": 54, "œ": 55, "š": 56}