Hugging Face's logo

robinhad
/
wav2vec2-xls-r-300m-uk

Automatic Speech Recognition
Transformers
PyTorch
Ukrainian
wav2vec2
common_voice
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
2
wav2vec2-xls-r-300m-uk / README.md
Yurii Paniv
Update name
72470a2
preview code
|
raw
history blame
11 kB
metadata
language:
  - uk
license: apache-2.0
tags:
  - automatic-speech-recognition
  - common_voice
  - generated_from_trainer
datasets:
  - common_voice
model-index:
  - name: wav2vec2-xls-r-300m-uk
    results:
      - task:
          name: Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice uk
          type: common_voice
          args: uk
        metrics:
          - name: Test WER
            type: wer
            value: 31.59

wav2vec2-xls-r-300m-uk

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the Common Voice 7.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4754
  • Wer: 0.3159
  • Cer: 0.0739

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0005
  • train_batch_size: 8
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 180.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Cer Validation Loss Wer
3.0162 0.12 500 1.0 3.1486 1.0
1.6532 0.24 1000 0.4583 1.3737 0.9951
1.3941 0.37 1500 0.3709 1.1033 0.9866
1.3275 0.49 2000 0.3487 1.0937 0.9540
1.2648 0.61 2500 0.3137 0.9403 0.9450
1.3085 0.73 3000 0.3090 0.9275 0.9288
1.1934 0.85 3500 0.2816 0.8737 0.8882
1.1909 0.98 4000 0.2780 0.8657 0.8698
1.0647 1.1 4500 0.2660 0.8246 0.8817
1.1362 1.22 5000 0.2711 0.8032 0.9086
1.0994 1.34 5500 0.2462 0.7719 0.8306
1.1 1.46 6000 0.2561 0.7853 0.8401
1.0629 1.59 6500 0.2459 0.7809 0.8245
1.1032 1.71 7000 0.2427 0.7638 0.8227
1.0171 1.83 7500 0.2332 0.7411 0.8087
1.0591 1.95 8000 0.2362 0.7332 0.8274
0.9725 2.07 8500 0.2217 0.7190 0.7847
1.03 2.2 9000 0.2356 0.7176 0.8255
0.9939 2.32 9500 0.2471 0.7189 0.8653
0.9564 2.44 10000 0.2270 0.7050 0.7984
0.966 2.56 10500 0.2200 0.6984 0.7738
0.9858 2.68 11000 0.2255 0.6885 0.8050
0.9484 2.81 11500 0.2183 0.6879 0.7646
0.9244 2.93 12000 0.2166 0.6590 0.7744
0.9224 3.05 12500 0.2035 0.6523 0.7477
0.9148 3.17 13000 0.2054 0.6522 0.7507
0.9227 3.29 13500 0.2037 0.6420 0.7541
0.8935 3.42 14000 0.2014 0.6442 0.7416
0.9257 3.54 14500 0.1986 0.6285 0.7263
0.9194 3.66 15000 0.1938 0.6117 0.72
0.9158 3.78 15500 0.1942 0.6197 0.7234
0.9079 3.9 16000 0.1939 0.6110 0.7187
0.8748 4.03 16500 0.1924 0.6182 0.7096
0.8646 4.15 17000 0.1894 0.6105 0.7057
0.8455 4.27 17500 0.1912 0.6236 0.7036
0.8922 4.39 18000 0.1921 0.5946 0.7341
0.892 4.51 18500 0.1869 0.5912 0.7142
0.8652 4.64 19000 0.1871 0.6005 0.6966
0.899 4.76 19500 0.1828 0.5773 0.6981
0.8552 4.88 20000 0.1805 0.5840 0.6875
0.8581 5.0 20500 0.1900 0.5941 0.7327
0.8571 5.12 21000 0.1846 0.5919 0.7049
0.7979 5.25 21500 0.1748 0.5704 0.6698
0.8348 5.37 22000 0.1789 0.5869 0.6766
0.7843 5.49 22500 0.1750 0.5732 0.6732
0.855 5.61 23000 0.1687 0.5448 0.6520
0.7774 5.73 23500 0.1759 0.5685 0.6818
0.8622 5.86 24000 0.1742 0.5598 0.6687
0.7968 5.98 24500 0.1699 0.5589 0.6577
0.8253 6.1 25000 0.1689 0.5601 0.6617
0.7947 6.22 25500 0.1678 0.5527 0.6472
0.8273 6.34 26000 0.1723 0.5426 0.6673
0.8085 6.47 26500 0.1682 0.5464 0.6476
0.8164 6.59 27000 0.1653 0.5460 0.6329
0.755 6.71 27500 0.1694 0.5420 0.6614
0.822 6.83 28000 0.1699 0.5540 0.6493
0.7957 6.95 28500 0.1630 0.5358 0.6373
0.7739 7.08 29000 0.1727 0.5662 0.6696
0.7833 7.2 29500 0.1594 0.5323 0.6227
0.7737 7.32 30000 0.1613 0.5349 0.6303
0.7697 7.44 30500 0.1623 0.5315 0.6386
0.7647 7.56 31000 0.1608 0.5346 0.6219
0.7123 7.69 31500 0.1561 0.5195 0.6110
0.7412 7.81 32000 0.1613 0.5385 0.6256
0.7702 7.93 32500 0.1614 0.5291 0.6343
0.7561 8.05 33000 0.1553 0.5044 0.6138
0.6707 8.78 36000 0.1484 0.4949 0.5881
0.719 9.52 39000 0.1508 0.5014 0.5959
0.6563 10.25 42000 0.1442 0.4852 0.5691
0.7166 10.98 45000 0.1437 0.4731 0.5718
0.6627 11.71 48000 0.1421 0.4787 0.5595
0.6642 12.45 51000 0.1353 0.4787 0.5417
0.615 13.18 54000 0.1324 0.4704 0.5297
0.6308 13.91 57000 0.1298 0.4570 0.5181
0.6169 14.64 60000 0.1291 0.4514 0.5106
0.5731 15.37 63000 0.1259 0.4462 0.5028
0.5328 16.11 66000 0.1246 0.4535 0.5023
0.5743 16.84 69000 0.1255 0.4555 0.5069
0.5363 17.57 72000 0.1214 0.4389 0.4915
0.5078 18.3 75000 0.1222 0.4525 0.4915
0.5075 19.03 78000 0.1208 0.4532 0.4871
0.5461 19.77 81000 0.1196 0.4401 0.4813
0.5044 20.5 84000 0.1144 0.4268 0.4654
0.4332 21.23 87000 0.1138 0.4383 0.4626
0.4671 21.96 90000 0.1118 0.4198 0.4547
0.4451 22.69 93000 0.1119 0.4426 0.4509
0.4319 23.43 96000 0.1096 0.4272 0.4472
0.3624 24.16 99000 0.1078 0.4347 0.4437
0.4512 24.89 102000 0.1102 0.4271 0.4471
0.4049 25.62 105000 0.1071 0.4207 0.4349
0.4134 26.35 108000 0.1061 0.4302 0.4351
0.4083 27.09 111000 0.1062 0.4583 0.4320
0.4618 27.82 114000 0.1046 0.4229 0.4281
0.4538 28.55 117000 0.1022 0.4060 0.42
0.4378 29.28 120000 0.1030 0.4239 0.4161
0.4062 30.01 123000 0.1012 0.4130 0.4171
0.3903 30.75 126000 0.1006 0.4134 0.4124
0.369 31.48 129000 0.0976 0.4163 0.4007
0.3896 32.21 132000 0.0986 0.3985 0.4015
0.3912 32.94 135000 0.0964 0.4103 0.3948
0.3995 33.67 138000 0.0975 0.3962 0.4024
0.4042 34.41 141000 0.0940 0.4196 0.3947
0.4055 35.14 144000 0.0949 0.3956 0.3882
0.3831 35.87 147000 0.0933 0.3962 0.3842
0.408 36.6 150000 0.0914 0.4019 0.3781
0.3632 37.34 153000 0.0917 0.4083 0.3814
0.381 38.07 156000 0.0914 0.4063 0.3738
0.3891 38.8 159000 0.0900 0.4060 0.3734
0.3668 39.53 162000 0.0893 0.4087 0.3701
0.3243 133.39 165000 0.3808 0.3460 0.0820
0.2861 135.81 168000 0.3986 0.3321 0.0788
0.2684 138.24 171000 0.4015 0.3299 0.0774
0.3027 140.66 174000 0.4023 0.3272 0.0771
0.2742 143.09 177000 0.4133 0.3273 0.0770
0.2339 145.51 180000 0.4287 0.3268 0.0771
0.2547 147.94 183000 0.4396 0.3254 0.0768
0.2072 150.36 186000 0.4586 0.3289 0.0774
0.2444 152.79 189000 0.4524 0.3239 0.0762
0.2272 155.21 192000 0.4620 0.3222 0.0759
0.2102 157.64 195000 0.4533 0.3212 0.0754
0.2231 160.06 198000 0.4563 0.3183 0.0745
0.2096 162.49 201000 0.4669 0.3183 0.0747
0.2173 164.92 204000 0.4704 0.3180 0.0746
0.1797 167.34 207000 0.4653 0.3169 0.0739
0.1841 169.77 210000 0.4726 0.3164 0.0737
0.1774 172.19 213000 0.4742 0.3162 0.0738
0.1819 174.62 216000 0.4720 0.3149 0.0737
0.1746 177.04 219000 0.4736 0.3153 0.0738
0.2101 179.47 222000 0.4756 0.3161 0.0738

Framework versions

  • Transformers 4.14.1
  • Pytorch 1.10.0
  • Datasets 1.16.1
  • Tokenizers 0.10.3