Hugging Face's logo

Amiran13
/
wav2vec2-large-xlsr-georgian_v1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Amiran13 commited on
Commit
15d03ba
•
1 Parent(s): 6e9aafe

Model save

Browse files
Files changed (3) hide show
  1. README.md +127 -4
  2. model.safetensors +1 -1
  3. runs/Nov28_16-50-44_4053f9fc2c05/events.out.tfevents.1701191936.4053f9fc2c05.1153.0 +0 -0
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1085
21
- - Wer: 0.2807
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 0.0003
41
  - train_batch_size: 16
42
  - eval_batch_size: 16
43
  - seed: 42
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 200
49
- - num_epochs: 20
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
@@ -175,6 +175,129 @@ The following hyperparameters were used during training:
175
  | 0.0668 | 19.54 | 12000 | 0.1086 | 0.2813 |
176
  | 0.069 | 19.7 | 12100 | 0.1087 | 0.2810 |
177
  | 0.0683 | 19.87 | 12200 | 0.1085 | 0.2807 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
178
 
179
 
180
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0992
21
+ - Wer: 0.2605
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
  - train_batch_size: 16
42
  - eval_batch_size: 16
43
  - seed: 42
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 200
49
+ - num_epochs: 40
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
 
175
  | 0.0668 | 19.54 | 12000 | 0.1086 | 0.2813 |
176
  | 0.069 | 19.7 | 12100 | 0.1087 | 0.2810 |
177
  | 0.0683 | 19.87 | 12200 | 0.1085 | 0.2807 |
178
+ | 0.1116 | 20.03 | 12300 | 0.1221 | 0.2978 |
179
+ | 0.0752 | 20.19 | 12400 | 0.1161 | 0.2956 |
180
+ | 0.0787 | 20.36 | 12500 | 0.1128 | 0.2927 |
181
+ | 0.0741 | 20.52 | 12600 | 0.1100 | 0.2922 |
182
+ | 0.0764 | 20.68 | 12700 | 0.1081 | 0.2906 |
183
+ | 0.0747 | 20.85 | 12800 | 0.1082 | 0.2896 |
184
+ | 0.0876 | 21.01 | 12900 | 0.1052 | 0.2896 |
185
+ | 0.0878 | 21.17 | 13000 | 0.1110 | 0.2950 |
186
+ | 0.0895 | 21.33 | 13100 | 0.1095 | 0.2934 |
187
+ | 0.0953 | 21.5 | 13200 | 0.1122 | 0.2981 |
188
+ | 0.0787 | 21.66 | 13300 | 0.1072 | 0.2896 |
189
+ | 0.0774 | 21.82 | 13400 | 0.1076 | 0.2880 |
190
+ | 0.0908 | 21.98 | 13500 | 0.1113 | 0.2916 |
191
+ | 0.0737 | 22.15 | 13600 | 0.1067 | 0.2870 |
192
+ | 0.0714 | 22.31 | 13700 | 0.1096 | 0.2864 |
193
+ | 0.0775 | 22.47 | 13800 | 0.1085 | 0.2868 |
194
+ | 0.0761 | 22.64 | 13900 | 0.1040 | 0.2852 |
195
+ | 0.0675 | 22.8 | 14000 | 0.1090 | 0.2836 |
196
+ | 0.0829 | 22.96 | 14100 | 0.1066 | 0.2814 |
197
+ | 0.0731 | 23.12 | 14200 | 0.1057 | 0.2835 |
198
+ | 0.058 | 23.29 | 14300 | 0.1059 | 0.2834 |
199
+ | 0.0833 | 23.45 | 14400 | 0.1056 | 0.2847 |
200
+ | 0.1007 | 23.62 | 14500 | 0.1225 | 0.3059 |
201
+ | 0.0896 | 23.78 | 14600 | 0.1088 | 0.2899 |
202
+ | 0.084 | 23.94 | 14700 | 0.1056 | 0.2834 |
203
+ | 0.0684 | 24.1 | 14800 | 0.1070 | 0.2865 |
204
+ | 0.0646 | 24.27 | 14900 | 0.1109 | 0.2862 |
205
+ | 0.0728 | 24.43 | 15000 | 0.1081 | 0.2876 |
206
+ | 0.0615 | 24.59 | 15100 | 0.1077 | 0.2846 |
207
+ | 0.0642 | 24.75 | 15200 | 0.1062 | 0.2842 |
208
+ | 0.0736 | 24.92 | 15300 | 0.1058 | 0.2864 |
209
+ | 0.0801 | 25.08 | 15400 | 0.1106 | 0.2844 |
210
+ | 0.0687 | 25.24 | 15500 | 0.1104 | 0.2836 |
211
+ | 0.0852 | 25.41 | 15600 | 0.1055 | 0.2826 |
212
+ | 0.078 | 25.57 | 15700 | 0.1069 | 0.2817 |
213
+ | 0.0815 | 25.73 | 15800 | 0.1040 | 0.2799 |
214
+ | 0.0863 | 25.89 | 15900 | 0.1074 | 0.2801 |
215
+ | 0.0603 | 26.06 | 16000 | 0.1044 | 0.2779 |
216
+ | 0.0625 | 26.22 | 16100 | 0.1036 | 0.2796 |
217
+ | 0.057 | 26.38 | 16200 | 0.1086 | 0.2802 |
218
+ | 0.0632 | 26.54 | 16300 | 0.1057 | 0.2790 |
219
+ | 0.0644 | 26.71 | 16400 | 0.1022 | 0.2750 |
220
+ | 0.0645 | 26.87 | 16500 | 0.1003 | 0.2766 |
221
+ | 0.0536 | 27.03 | 16600 | 0.1051 | 0.2786 |
222
+ | 0.058 | 27.2 | 16700 | 0.1051 | 0.2790 |
223
+ | 0.052 | 27.36 | 16800 | 0.1034 | 0.2748 |
224
+ | 0.0514 | 27.52 | 16900 | 0.1027 | 0.2751 |
225
+ | 0.0593 | 27.68 | 17000 | 0.1036 | 0.2795 |
226
+ | 0.0577 | 27.85 | 17100 | 0.1025 | 0.2770 |
227
+ | 0.0694 | 28.01 | 17200 | 0.1008 | 0.2733 |
228
+ | 0.0641 | 28.17 | 17300 | 0.1088 | 0.2760 |
229
+ | 0.0566 | 28.33 | 17400 | 0.1092 | 0.2759 |
230
+ | 0.073 | 28.5 | 17500 | 0.1120 | 0.2788 |
231
+ | 0.0632 | 28.66 | 17600 | 0.1056 | 0.2764 |
232
+ | 0.0674 | 28.82 | 17700 | 0.1021 | 0.2739 |
233
+ | 0.0663 | 28.99 | 17800 | 0.1033 | 0.2733 |
234
+ | 0.0544 | 29.15 | 17900 | 0.1053 | 0.2721 |
235
+ | 0.0583 | 29.31 | 18000 | 0.1033 | 0.2732 |
236
+ | 0.0652 | 29.47 | 18100 | 0.1015 | 0.2728 |
237
+ | 0.0577 | 29.64 | 18200 | 0.1029 | 0.2730 |
238
+ | 0.1068 | 29.8 | 18300 | 0.1297 | 0.2950 |
239
+ | 0.0805 | 29.97 | 18400 | 0.1113 | 0.2792 |
240
+ | 0.0689 | 30.13 | 18500 | 0.1077 | 0.2789 |
241
+ | 0.0688 | 30.29 | 18600 | 0.1069 | 0.2777 |
242
+ | 0.0589 | 30.45 | 18700 | 0.1071 | 0.2757 |
243
+ | 0.049 | 30.62 | 18800 | 0.1077 | 0.2749 |
244
+ | 0.0534 | 30.78 | 18900 | 0.1046 | 0.2703 |
245
+ | 0.0506 | 30.94 | 19000 | 0.1039 | 0.2728 |
246
+ | 0.0534 | 31.11 | 19100 | 0.1036 | 0.2719 |
247
+ | 0.0453 | 31.27 | 19200 | 0.1064 | 0.2717 |
248
+ | 0.0514 | 31.43 | 19300 | 0.1034 | 0.2712 |
249
+ | 0.0579 | 31.59 | 19400 | 0.1065 | 0.2726 |
250
+ | 0.0491 | 31.76 | 19500 | 0.1054 | 0.2749 |
251
+ | 0.0547 | 31.92 | 19600 | 0.1023 | 0.2720 |
252
+ | 0.08 | 32.08 | 19700 | 0.1037 | 0.2707 |
253
+ | 0.0649 | 32.24 | 19800 | 0.1037 | 0.2702 |
254
+ | 0.064 | 32.41 | 19900 | 0.1053 | 0.2714 |
255
+ | 0.064 | 32.57 | 20000 | 0.1035 | 0.2691 |
256
+ | 0.0658 | 32.73 | 20100 | 0.1017 | 0.2663 |
257
+ | 0.0636 | 32.9 | 20200 | 0.1031 | 0.2680 |
258
+ | 0.0439 | 33.06 | 20300 | 0.1010 | 0.2668 |
259
+ | 0.0518 | 33.22 | 20400 | 0.1016 | 0.2691 |
260
+ | 0.0498 | 33.38 | 20500 | 0.1028 | 0.2682 |
261
+ | 0.0516 | 33.55 | 20600 | 0.1009 | 0.2679 |
262
+ | 0.0534 | 33.71 | 20700 | 0.1022 | 0.2672 |
263
+ | 0.0464 | 33.87 | 20800 | 0.1029 | 0.2661 |
264
+ | 0.0522 | 34.03 | 20900 | 0.1002 | 0.2668 |
265
+ | 0.0458 | 34.2 | 21000 | 0.0981 | 0.2644 |
266
+ | 0.0425 | 34.36 | 21100 | 0.1004 | 0.2659 |
267
+ | 0.0461 | 34.52 | 21200 | 0.1009 | 0.2650 |
268
+ | 0.0436 | 34.69 | 21300 | 0.1007 | 0.2652 |
269
+ | 0.0507 | 34.85 | 21400 | 0.1005 | 0.2655 |
270
+ | 0.0437 | 35.01 | 21500 | 0.0992 | 0.2648 |
271
+ | 0.0492 | 35.17 | 21600 | 0.1022 | 0.2655 |
272
+ | 0.0456 | 35.34 | 21700 | 0.1030 | 0.2639 |
273
+ | 0.0421 | 35.5 | 21800 | 0.1054 | 0.2639 |
274
+ | 0.0759 | 35.67 | 21900 | 0.1253 | 0.2760 |
275
+ | 0.059 | 35.83 | 22000 | 0.1125 | 0.2710 |
276
+ | 0.0515 | 35.99 | 22100 | 0.1073 | 0.2667 |
277
+ | 0.0583 | 36.16 | 22200 | 0.1085 | 0.2671 |
278
+ | 0.0603 | 36.32 | 22300 | 0.1047 | 0.2658 |
279
+ | 0.0575 | 36.48 | 22400 | 0.1034 | 0.2652 |
280
+ | 0.0605 | 36.64 | 22500 | 0.1044 | 0.2656 |
281
+ | 0.0545 | 36.81 | 22600 | 0.1057 | 0.2649 |
282
+ | 0.0583 | 36.97 | 22700 | 0.1033 | 0.2641 |
283
+ | 0.0492 | 37.13 | 22800 | 0.1039 | 0.2641 |
284
+ | 0.0561 | 37.29 | 22900 | 0.1027 | 0.2640 |
285
+ | 0.0447 | 37.46 | 23000 | 0.1023 | 0.2631 |
286
+ | 0.0521 | 37.62 | 23100 | 0.1010 | 0.2636 |
287
+ | 0.0482 | 37.78 | 23200 | 0.1021 | 0.2635 |
288
+ | 0.0468 | 37.95 | 23300 | 0.0999 | 0.2631 |
289
+ | 0.0473 | 38.11 | 23400 | 0.1016 | 0.2629 |
290
+ | 0.0416 | 38.27 | 23500 | 0.1003 | 0.2621 |
291
+ | 0.0491 | 38.43 | 23600 | 0.1022 | 0.2618 |
292
+ | 0.0394 | 38.6 | 23700 | 0.1017 | 0.2622 |
293
+ | 0.0389 | 38.76 | 23800 | 0.1011 | 0.2620 |
294
+ | 0.0381 | 38.92 | 23900 | 0.0992 | 0.2608 |
295
+ | 0.0557 | 39.08 | 24000 | 0.0999 | 0.2613 |
296
+ | 0.0545 | 39.25 | 24100 | 0.1002 | 0.2608 |
297
+ | 0.0633 | 39.41 | 24200 | 0.0997 | 0.2607 |
298
+ | 0.0471 | 39.57 | 24300 | 0.0994 | 0.2609 |
299
+ | 0.0672 | 39.74 | 24400 | 0.0991 | 0.2606 |
300
+ | 0.066 | 39.9 | 24500 | 0.0992 | 0.2605 |
301
 
302
 
303
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67f345c830654f8672e9c0d47ca2dda3f99e590a75f88723433e2d30a6cf2f86
3
  size 1261975580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66c9d78a1c791ee364d68a05c18e682f18d74f9c3b39e3d7f07f49a2e2b78a2
3
  size 1261975580
runs/Nov28_16-50-44_4053f9fc2c05/events.out.tfevents.1701191936.4053f9fc2c05.1153.0 CHANGED
Binary files a/runs/Nov28_16-50-44_4053f9fc2c05/events.out.tfevents.1701191936.4053f9fc2c05.1153.0 and b/runs/Nov28_16-50-44_4053f9fc2c05/events.out.tfevents.1701191936.4053f9fc2c05.1153.0 differ