Yurii Paniv
commited on
Commit
•
7b86b4e
1
Parent(s):
0702682
Update model to WER 31.59%
Browse files- README.md +156 -22
- added_tokens.json +1 -0
- all_results.json +15 -0
- config.json +14 -8
- eval_results.json +10 -0
- optimizer.pt +0 -3
- preprocessor_config.json +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +0 -3
- scaler.pt +0 -3
- scheduler.pt +0 -3
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
- train_results.json +8 -0
- trainer_state.json +0 -0
- training_args.bin +2 -2
- vocab.json +1 -1
README.md
CHANGED
|
@@ -1,60 +1,194 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
| 4 |
tags:
|
| 5 |
- automatic-speech-recognition
|
| 6 |
- common_voice
|
| 7 |
-
|
| 8 |
datasets:
|
| 9 |
- common_voice
|
| 10 |
-
|
| 11 |
model-index:
|
| 12 |
- name: wav2vec2-xls-r-300m-uk
|
| 13 |
results: []
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
-
|
| 18 |
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
|
| 20 |
# wav2vec2-xls-r-300m-uk
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the Common Voice 7.0 dataset.
|
| 23 |
-
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
-
|
| 26 |
-
-
|
| 27 |
-
|
| 28 |
-
- Wer: 0.152833
|
| 29 |
|
| 30 |
## Model description
|
|
|
|
| 31 |
More information needed
|
| 32 |
|
| 33 |
## Intended uses & limitations
|
|
|
|
| 34 |
More information needed
|
| 35 |
|
| 36 |
## Training and evaluation data
|
|
|
|
| 37 |
More information needed
|
| 38 |
|
| 39 |
## Training procedure
|
| 40 |
|
| 41 |
### Training hyperparameters
|
| 42 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
| 46 |
-
|
|
| 47 |
-
|
| 48 |
-
|
|
| 49 |
-
|
|
| 50 |
-
|
|
| 51 |
-
|
|
| 52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
-
- Transformers 4.
|
| 57 |
- Pytorch 1.10.0
|
| 58 |
-
- Datasets 1.
|
| 59 |
-
|
| 60 |
-
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- uk
|
| 4 |
+
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
- automatic-speech-recognition
|
| 7 |
- common_voice
|
| 8 |
+
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- common_voice
|
|
|
|
| 11 |
model-index:
|
| 12 |
- name: wav2vec2-xls-r-300m-uk
|
| 13 |
results: []
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 17 |
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
|
| 19 |
# wav2vec2-xls-r-300m-uk
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the Common Voice 7.0 dataset.
|
|
|
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.4754
|
| 24 |
+
- Wer: 0.3159
|
| 25 |
+
- Cer: 0.0739
|
|
|
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
+
|
| 29 |
More information needed
|
| 30 |
|
| 31 |
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
More information needed
|
| 34 |
|
| 35 |
## Training and evaluation data
|
| 36 |
+
|
| 37 |
More information needed
|
| 38 |
|
| 39 |
## Training procedure
|
| 40 |
|
| 41 |
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 0.0005
|
| 45 |
+
- train_batch_size: 8
|
| 46 |
+
- eval_batch_size: 4
|
| 47 |
+
- seed: 42
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- lr_scheduler_warmup_steps: 500
|
| 51 |
+
- num_epochs: 180.0
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
+
| Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
|
| 57 |
+
|:-------------:|:------:|:------:|:------:|:---------------:|:------:|
|
| 58 |
+
| 3.0162 | 0.12 | 500 | 1.0 | 3.1486 | 1.0 |
|
| 59 |
+
| 1.6532 | 0.24 | 1000 | 0.4583 | 1.3737 | 0.9951 |
|
| 60 |
+
| 1.3941 | 0.37 | 1500 | 0.3709 | 1.1033 | 0.9866 |
|
| 61 |
+
| 1.3275 | 0.49 | 2000 | 0.3487 | 1.0937 | 0.9540 |
|
| 62 |
+
| 1.2648 | 0.61 | 2500 | 0.3137 | 0.9403 | 0.9450 |
|
| 63 |
+
| 1.3085 | 0.73 | 3000 | 0.3090 | 0.9275 | 0.9288 |
|
| 64 |
+
| 1.1934 | 0.85 | 3500 | 0.2816 | 0.8737 | 0.8882 |
|
| 65 |
+
| 1.1909 | 0.98 | 4000 | 0.2780 | 0.8657 | 0.8698 |
|
| 66 |
+
| 1.0647 | 1.1 | 4500 | 0.2660 | 0.8246 | 0.8817 |
|
| 67 |
+
| 1.1362 | 1.22 | 5000 | 0.2711 | 0.8032 | 0.9086 |
|
| 68 |
+
| 1.0994 | 1.34 | 5500 | 0.2462 | 0.7719 | 0.8306 |
|
| 69 |
+
| 1.1 | 1.46 | 6000 | 0.2561 | 0.7853 | 0.8401 |
|
| 70 |
+
| 1.0629 | 1.59 | 6500 | 0.2459 | 0.7809 | 0.8245 |
|
| 71 |
+
| 1.1032 | 1.71 | 7000 | 0.2427 | 0.7638 | 0.8227 |
|
| 72 |
+
| 1.0171 | 1.83 | 7500 | 0.2332 | 0.7411 | 0.8087 |
|
| 73 |
+
| 1.0591 | 1.95 | 8000 | 0.2362 | 0.7332 | 0.8274 |
|
| 74 |
+
| 0.9725 | 2.07 | 8500 | 0.2217 | 0.7190 | 0.7847 |
|
| 75 |
+
| 1.03 | 2.2 | 9000 | 0.2356 | 0.7176 | 0.8255 |
|
| 76 |
+
| 0.9939 | 2.32 | 9500 | 0.2471 | 0.7189 | 0.8653 |
|
| 77 |
+
| 0.9564 | 2.44 | 10000 | 0.2270 | 0.7050 | 0.7984 |
|
| 78 |
+
| 0.966 | 2.56 | 10500 | 0.2200 | 0.6984 | 0.7738 |
|
| 79 |
+
| 0.9858 | 2.68 | 11000 | 0.2255 | 0.6885 | 0.8050 |
|
| 80 |
+
| 0.9484 | 2.81 | 11500 | 0.2183 | 0.6879 | 0.7646 |
|
| 81 |
+
| 0.9244 | 2.93 | 12000 | 0.2166 | 0.6590 | 0.7744 |
|
| 82 |
+
| 0.9224 | 3.05 | 12500 | 0.2035 | 0.6523 | 0.7477 |
|
| 83 |
+
| 0.9148 | 3.17 | 13000 | 0.2054 | 0.6522 | 0.7507 |
|
| 84 |
+
| 0.9227 | 3.29 | 13500 | 0.2037 | 0.6420 | 0.7541 |
|
| 85 |
+
| 0.8935 | 3.42 | 14000 | 0.2014 | 0.6442 | 0.7416 |
|
| 86 |
+
| 0.9257 | 3.54 | 14500 | 0.1986 | 0.6285 | 0.7263 |
|
| 87 |
+
| 0.9194 | 3.66 | 15000 | 0.1938 | 0.6117 | 0.72 |
|
| 88 |
+
| 0.9158 | 3.78 | 15500 | 0.1942 | 0.6197 | 0.7234 |
|
| 89 |
+
| 0.9079 | 3.9 | 16000 | 0.1939 | 0.6110 | 0.7187 |
|
| 90 |
+
| 0.8748 | 4.03 | 16500 | 0.1924 | 0.6182 | 0.7096 |
|
| 91 |
+
| 0.8646 | 4.15 | 17000 | 0.1894 | 0.6105 | 0.7057 |
|
| 92 |
+
| 0.8455 | 4.27 | 17500 | 0.1912 | 0.6236 | 0.7036 |
|
| 93 |
+
| 0.8922 | 4.39 | 18000 | 0.1921 | 0.5946 | 0.7341 |
|
| 94 |
+
| 0.892 | 4.51 | 18500 | 0.1869 | 0.5912 | 0.7142 |
|
| 95 |
+
| 0.8652 | 4.64 | 19000 | 0.1871 | 0.6005 | 0.6966 |
|
| 96 |
+
| 0.899 | 4.76 | 19500 | 0.1828 | 0.5773 | 0.6981 |
|
| 97 |
+
| 0.8552 | 4.88 | 20000 | 0.1805 | 0.5840 | 0.6875 |
|
| 98 |
+
| 0.8581 | 5.0 | 20500 | 0.1900 | 0.5941 | 0.7327 |
|
| 99 |
+
| 0.8571 | 5.12 | 21000 | 0.1846 | 0.5919 | 0.7049 |
|
| 100 |
+
| 0.7979 | 5.25 | 21500 | 0.1748 | 0.5704 | 0.6698 |
|
| 101 |
+
| 0.8348 | 5.37 | 22000 | 0.1789 | 0.5869 | 0.6766 |
|
| 102 |
+
| 0.7843 | 5.49 | 22500 | 0.1750 | 0.5732 | 0.6732 |
|
| 103 |
+
| 0.855 | 5.61 | 23000 | 0.1687 | 0.5448 | 0.6520 |
|
| 104 |
+
| 0.7774 | 5.73 | 23500 | 0.1759 | 0.5685 | 0.6818 |
|
| 105 |
+
| 0.8622 | 5.86 | 24000 | 0.1742 | 0.5598 | 0.6687 |
|
| 106 |
+
| 0.7968 | 5.98 | 24500 | 0.1699 | 0.5589 | 0.6577 |
|
| 107 |
+
| 0.8253 | 6.1 | 25000 | 0.1689 | 0.5601 | 0.6617 |
|
| 108 |
+
| 0.7947 | 6.22 | 25500 | 0.1678 | 0.5527 | 0.6472 |
|
| 109 |
+
| 0.8273 | 6.34 | 26000 | 0.1723 | 0.5426 | 0.6673 |
|
| 110 |
+
| 0.8085 | 6.47 | 26500 | 0.1682 | 0.5464 | 0.6476 |
|
| 111 |
+
| 0.8164 | 6.59 | 27000 | 0.1653 | 0.5460 | 0.6329 |
|
| 112 |
+
| 0.755 | 6.71 | 27500 | 0.1694 | 0.5420 | 0.6614 |
|
| 113 |
+
| 0.822 | 6.83 | 28000 | 0.1699 | 0.5540 | 0.6493 |
|
| 114 |
+
| 0.7957 | 6.95 | 28500 | 0.1630 | 0.5358 | 0.6373 |
|
| 115 |
+
| 0.7739 | 7.08 | 29000 | 0.1727 | 0.5662 | 0.6696 |
|
| 116 |
+
| 0.7833 | 7.2 | 29500 | 0.1594 | 0.5323 | 0.6227 |
|
| 117 |
+
| 0.7737 | 7.32 | 30000 | 0.1613 | 0.5349 | 0.6303 |
|
| 118 |
+
| 0.7697 | 7.44 | 30500 | 0.1623 | 0.5315 | 0.6386 |
|
| 119 |
+
| 0.7647 | 7.56 | 31000 | 0.1608 | 0.5346 | 0.6219 |
|
| 120 |
+
| 0.7123 | 7.69 | 31500 | 0.1561 | 0.5195 | 0.6110 |
|
| 121 |
+
| 0.7412 | 7.81 | 32000 | 0.1613 | 0.5385 | 0.6256 |
|
| 122 |
+
| 0.7702 | 7.93 | 32500 | 0.1614 | 0.5291 | 0.6343 |
|
| 123 |
+
| 0.7561 | 8.05 | 33000 | 0.1553 | 0.5044 | 0.6138 |
|
| 124 |
+
| 0.6707 | 8.78 | 36000 | 0.1484 | 0.4949 | 0.5881 |
|
| 125 |
+
| 0.719 | 9.52 | 39000 | 0.1508 | 0.5014 | 0.5959 |
|
| 126 |
+
| 0.6563 | 10.25 | 42000 | 0.1442 | 0.4852 | 0.5691 |
|
| 127 |
+
| 0.7166 | 10.98 | 45000 | 0.1437 | 0.4731 | 0.5718 |
|
| 128 |
+
| 0.6627 | 11.71 | 48000 | 0.1421 | 0.4787 | 0.5595 |
|
| 129 |
+
| 0.6642 | 12.45 | 51000 | 0.1353 | 0.4787 | 0.5417 |
|
| 130 |
+
| 0.615 | 13.18 | 54000 | 0.1324 | 0.4704 | 0.5297 |
|
| 131 |
+
| 0.6308 | 13.91 | 57000 | 0.1298 | 0.4570 | 0.5181 |
|
| 132 |
+
| 0.6169 | 14.64 | 60000 | 0.1291 | 0.4514 | 0.5106 |
|
| 133 |
+
| 0.5731 | 15.37 | 63000 | 0.1259 | 0.4462 | 0.5028 |
|
| 134 |
+
| 0.5328 | 16.11 | 66000 | 0.1246 | 0.4535 | 0.5023 |
|
| 135 |
+
| 0.5743 | 16.84 | 69000 | 0.1255 | 0.4555 | 0.5069 |
|
| 136 |
+
| 0.5363 | 17.57 | 72000 | 0.1214 | 0.4389 | 0.4915 |
|
| 137 |
+
| 0.5078 | 18.3 | 75000 | 0.1222 | 0.4525 | 0.4915 |
|
| 138 |
+
| 0.5075 | 19.03 | 78000 | 0.1208 | 0.4532 | 0.4871 |
|
| 139 |
+
| 0.5461 | 19.77 | 81000 | 0.1196 | 0.4401 | 0.4813 |
|
| 140 |
+
| 0.5044 | 20.5 | 84000 | 0.1144 | 0.4268 | 0.4654 |
|
| 141 |
+
| 0.4332 | 21.23 | 87000 | 0.1138 | 0.4383 | 0.4626 |
|
| 142 |
+
| 0.4671 | 21.96 | 90000 | 0.1118 | 0.4198 | 0.4547 |
|
| 143 |
+
| 0.4451 | 22.69 | 93000 | 0.1119 | 0.4426 | 0.4509 |
|
| 144 |
+
| 0.4319 | 23.43 | 96000 | 0.1096 | 0.4272 | 0.4472 |
|
| 145 |
+
| 0.3624 | 24.16 | 99000 | 0.1078 | 0.4347 | 0.4437 |
|
| 146 |
+
| 0.4512 | 24.89 | 102000 | 0.1102 | 0.4271 | 0.4471 |
|
| 147 |
+
| 0.4049 | 25.62 | 105000 | 0.1071 | 0.4207 | 0.4349 |
|
| 148 |
+
| 0.4134 | 26.35 | 108000 | 0.1061 | 0.4302 | 0.4351 |
|
| 149 |
+
| 0.4083 | 27.09 | 111000 | 0.1062 | 0.4583 | 0.4320 |
|
| 150 |
+
| 0.4618 | 27.82 | 114000 | 0.1046 | 0.4229 | 0.4281 |
|
| 151 |
+
| 0.4538 | 28.55 | 117000 | 0.1022 | 0.4060 | 0.42 |
|
| 152 |
+
| 0.4378 | 29.28 | 120000 | 0.1030 | 0.4239 | 0.4161 |
|
| 153 |
+
| 0.4062 | 30.01 | 123000 | 0.1012 | 0.4130 | 0.4171 |
|
| 154 |
+
| 0.3903 | 30.75 | 126000 | 0.1006 | 0.4134 | 0.4124 |
|
| 155 |
+
| 0.369 | 31.48 | 129000 | 0.0976 | 0.4163 | 0.4007 |
|
| 156 |
+
| 0.3896 | 32.21 | 132000 | 0.0986 | 0.3985 | 0.4015 |
|
| 157 |
+
| 0.3912 | 32.94 | 135000 | 0.0964 | 0.4103 | 0.3948 |
|
| 158 |
+
| 0.3995 | 33.67 | 138000 | 0.0975 | 0.3962 | 0.4024 |
|
| 159 |
+
| 0.4042 | 34.41 | 141000 | 0.0940 | 0.4196 | 0.3947 |
|
| 160 |
+
| 0.4055 | 35.14 | 144000 | 0.0949 | 0.3956 | 0.3882 |
|
| 161 |
+
| 0.3831 | 35.87 | 147000 | 0.0933 | 0.3962 | 0.3842 |
|
| 162 |
+
| 0.408 | 36.6 | 150000 | 0.0914 | 0.4019 | 0.3781 |
|
| 163 |
+
| 0.3632 | 37.34 | 153000 | 0.0917 | 0.4083 | 0.3814 |
|
| 164 |
+
| 0.381 | 38.07 | 156000 | 0.0914 | 0.4063 | 0.3738 |
|
| 165 |
+
| 0.3891 | 38.8 | 159000 | 0.0900 | 0.4060 | 0.3734 |
|
| 166 |
+
| 0.3668 | 39.53 | 162000 | 0.0893 | 0.4087 | 0.3701 |
|
| 167 |
+
| 0.3243 | 133.39 | 165000 | 0.3808 | 0.3460 | 0.0820 |
|
| 168 |
+
| 0.2861 | 135.81 | 168000 | 0.3986 | 0.3321 | 0.0788 |
|
| 169 |
+
| 0.2684 | 138.24 | 171000 | 0.4015 | 0.3299 | 0.0774 |
|
| 170 |
+
| 0.3027 | 140.66 | 174000 | 0.4023 | 0.3272 | 0.0771 |
|
| 171 |
+
| 0.2742 | 143.09 | 177000 | 0.4133 | 0.3273 | 0.0770 |
|
| 172 |
+
| 0.2339 | 145.51 | 180000 | 0.4287 | 0.3268 | 0.0771 |
|
| 173 |
+
| 0.2547 | 147.94 | 183000 | 0.4396 | 0.3254 | 0.0768 |
|
| 174 |
+
| 0.2072 | 150.36 | 186000 | 0.4586 | 0.3289 | 0.0774 |
|
| 175 |
+
| 0.2444 | 152.79 | 189000 | 0.4524 | 0.3239 | 0.0762 |
|
| 176 |
+
| 0.2272 | 155.21 | 192000 | 0.4620 | 0.3222 | 0.0759 |
|
| 177 |
+
| 0.2102 | 157.64 | 195000 | 0.4533 | 0.3212 | 0.0754 |
|
| 178 |
+
| 0.2231 | 160.06 | 198000 | 0.4563 | 0.3183 | 0.0745 |
|
| 179 |
+
| 0.2096 | 162.49 | 201000 | 0.4669 | 0.3183 | 0.0747 |
|
| 180 |
+
| 0.2173 | 164.92 | 204000 | 0.4704 | 0.3180 | 0.0746 |
|
| 181 |
+
| 0.1797 | 167.34 | 207000 | 0.4653 | 0.3169 | 0.0739 |
|
| 182 |
+
| 0.1841 | 169.77 | 210000 | 0.4726 | 0.3164 | 0.0737 |
|
| 183 |
+
| 0.1774 | 172.19 | 213000 | 0.4742 | 0.3162 | 0.0738 |
|
| 184 |
+
| 0.1819 | 174.62 | 216000 | 0.4720 | 0.3149 | 0.0737 |
|
| 185 |
+
| 0.1746 | 177.04 | 219000 | 0.4736 | 0.3153 | 0.0738 |
|
| 186 |
+
| 0.2101 | 179.47 | 222000 | 0.4756 | 0.3161 | 0.0738 |
|
| 187 |
+
|
| 188 |
|
| 189 |
### Framework versions
|
| 190 |
|
| 191 |
+
- Transformers 4.14.1
|
| 192 |
- Pytorch 1.10.0
|
| 193 |
+
- Datasets 1.16.1
|
| 194 |
+
- Tokenizers 0.10.3
|
|
|
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<s>": 37, "</s>": 38}
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 180.0,
|
| 3 |
+
"eval_cer": 0.07386836134410645,
|
| 4 |
+
"eval_loss": 0.4753616452217102,
|
| 5 |
+
"eval_runtime": 157.9734,
|
| 6 |
+
"eval_samples": 4193,
|
| 7 |
+
"eval_samples_per_second": 26.542,
|
| 8 |
+
"eval_steps_per_second": 6.64,
|
| 9 |
+
"eval_wer": 0.31588907014681894,
|
| 10 |
+
"train_loss": 0.061750437557927515,
|
| 11 |
+
"train_runtime": 29496.4676,
|
| 12 |
+
"train_samples": 9889,
|
| 13 |
+
"train_samples_per_second": 60.347,
|
| 14 |
+
"train_steps_per_second": 7.549
|
| 15 |
+
}
|
config.json
CHANGED
|
@@ -1,11 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
| 3 |
"activation_dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
| 4 |
"apply_spec_augment": true,
|
| 5 |
"architectures": [
|
| 6 |
"Wav2Vec2ForCTC"
|
| 7 |
],
|
| 8 |
-
"attention_dropout": 0.
|
| 9 |
"bos_token_id": 1,
|
| 10 |
"classifier_proj_size": 256,
|
| 11 |
"codevector_dim": 768,
|
|
@@ -46,22 +49,24 @@
|
|
| 46 |
"feat_extract_activation": "gelu",
|
| 47 |
"feat_extract_dropout": 0.0,
|
| 48 |
"feat_extract_norm": "layer",
|
| 49 |
-
"feat_proj_dropout": 0.
|
| 50 |
"feat_quantizer_dropout": 0.0,
|
| 51 |
"final_dropout": 0.0,
|
| 52 |
-
"gradient_checkpointing": false,
|
| 53 |
"hidden_act": "gelu",
|
| 54 |
-
"hidden_dropout": 0.
|
| 55 |
"hidden_size": 1024,
|
| 56 |
"initializer_range": 0.02,
|
| 57 |
"intermediate_size": 4096,
|
| 58 |
"layer_norm_eps": 1e-05,
|
| 59 |
"layerdrop": 0.0,
|
| 60 |
-
"mask_feature_length":
|
| 61 |
-
"
|
|
|
|
| 62 |
"mask_time_length": 10,
|
| 63 |
-
"
|
|
|
|
| 64 |
"model_type": "wav2vec2",
|
|
|
|
| 65 |
"num_attention_heads": 16,
|
| 66 |
"num_codevector_groups": 2,
|
| 67 |
"num_codevectors_per_group": 320,
|
|
@@ -70,10 +75,11 @@
|
|
| 70 |
"num_feat_extract_layers": 7,
|
| 71 |
"num_hidden_layers": 24,
|
| 72 |
"num_negatives": 100,
|
|
|
|
| 73 |
"pad_token_id": 36,
|
| 74 |
"proj_codevector_dim": 768,
|
| 75 |
"torch_dtype": "float32",
|
| 76 |
-
"transformers_version": "4.
|
| 77 |
"use_weighted_layer_sum": false,
|
| 78 |
"vocab_size": 39
|
| 79 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
| 3 |
"activation_dropout": 0.0,
|
| 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": 0.0,
|
| 12 |
"bos_token_id": 1,
|
| 13 |
"classifier_proj_size": 256,
|
| 14 |
"codevector_dim": 768,
|
|
|
|
| 49 |
"feat_extract_activation": "gelu",
|
| 50 |
"feat_extract_dropout": 0.0,
|
| 51 |
"feat_extract_norm": "layer",
|
| 52 |
+
"feat_proj_dropout": 0.0,
|
| 53 |
"feat_quantizer_dropout": 0.0,
|
| 54 |
"final_dropout": 0.0,
|
|
|
|
| 55 |
"hidden_act": "gelu",
|
| 56 |
+
"hidden_dropout": 0.0,
|
| 57 |
"hidden_size": 1024,
|
| 58 |
"initializer_range": 0.02,
|
| 59 |
"intermediate_size": 4096,
|
| 60 |
"layer_norm_eps": 1e-05,
|
| 61 |
"layerdrop": 0.0,
|
| 62 |
+
"mask_feature_length": 64,
|
| 63 |
+
"mask_feature_min_masks": 0,
|
| 64 |
+
"mask_feature_prob": 0.1,
|
| 65 |
"mask_time_length": 10,
|
| 66 |
+
"mask_time_min_masks": 2,
|
| 67 |
+
"mask_time_prob": 0.3,
|
| 68 |
"model_type": "wav2vec2",
|
| 69 |
+
"num_adapter_layers": 3,
|
| 70 |
"num_attention_heads": 16,
|
| 71 |
"num_codevector_groups": 2,
|
| 72 |
"num_codevectors_per_group": 320,
|
|
|
|
| 75 |
"num_feat_extract_layers": 7,
|
| 76 |
"num_hidden_layers": 24,
|
| 77 |
"num_negatives": 100,
|
| 78 |
+
"output_hidden_size": 1024,
|
| 79 |
"pad_token_id": 36,
|
| 80 |
"proj_codevector_dim": 768,
|
| 81 |
"torch_dtype": "float32",
|
| 82 |
+
"transformers_version": "4.14.1",
|
| 83 |
"use_weighted_layer_sum": false,
|
| 84 |
"vocab_size": 39
|
| 85 |
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 180.0,
|
| 3 |
+
"eval_cer": 0.07386836134410645,
|
| 4 |
+
"eval_loss": 0.4753616452217102,
|
| 5 |
+
"eval_runtime": 157.9734,
|
| 6 |
+
"eval_samples": 4193,
|
| 7 |
+
"eval_samples_per_second": 26.542,
|
| 8 |
+
"eval_steps_per_second": 6.64,
|
| 9 |
+
"eval_wer": 0.31588907014681894
|
| 10 |
+
}
|
optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0fbd68c9108bdd7f2b74d2d6ab60ec454155756c1066837141fb986be18d13b0
|
| 3 |
-
size 2490378769
|
|
|
|
|
|
|
|
|
|
|
|
preprocessor_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
"feature_size": 1,
|
| 5 |
"padding_side": "right",
|
| 6 |
-
"padding_value": 0
|
| 7 |
"return_attention_mask": true,
|
| 8 |
"sampling_rate": 16000
|
| 9 |
}
|
|
|
|
| 3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
"feature_size": 1,
|
| 5 |
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
"return_attention_mask": true,
|
| 8 |
"sampling_rate": 16000
|
| 9 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262083569
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fec030a8b93bf8846c4285ae762c4b49729965350f37f48ffae03557b3e1d55
|
| 3 |
size 1262083569
|
rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:76eba952d902f592e5dc53b1ace73547fece6bddedfb82abd6d368838cc3983f
|
| 3 |
-
size 14567
|
|
|
|
|
|
|
|
|
|
|
|
scaler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:12ab3ab57bdd4de9271b2ed77c5b527f019219b09da8c0a67492f35863f058ca
|
| 3 |
-
size 559
|
|
|
|
|
|
|
|
|
|
|
|
scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8cd458f9d8a9355ed82afe3dc4a8877431efaf85b6481a523d12fee5200e931c
|
| 3 |
-
size 623
|
|
|
|
|
|
|
|
|
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./wav2vec2-xls-r-300m-uk", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 180.0,
|
| 3 |
+
"train_loss": 0.061750437557927515,
|
| 4 |
+
"train_runtime": 29496.4676,
|
| 5 |
+
"train_samples": 9889,
|
| 6 |
+
"train_samples_per_second": 60.347,
|
| 7 |
+
"train_steps_per_second": 7.549
|
| 8 |
+
}
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4eaf0322682a5dc5352958832b28880acc9c8d1d79076deb7e8bccb9368ac2f8
|
| 3 |
+
size 2927
|
vocab.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"
|
|
|
|
| 1 |
+
{"ʼ": 1, "а": 2, "б": 3, "в": 4, "г": 5, "д": 6, "е": 7, "ж": 8, "з": 9, "и": 10, "й": 11, "к": 12, "л": 13, "м": 14, "н": 15, "о": 16, "п": 17, "р": 18, "с": 19, "т": 20, "у": 21, "ф": 22, "х": 23, "ц": 24, "ч": 25, "ш": 26, "щ": 27, "ь": 28, "ю": 29, "я": 30, "є": 31, "і": 32, "ї": 33, "ґ": 34, "|": 0, "[UNK]": 35, "[PAD]": 36}
|