<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
model_syllable_onSet0
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1789
- 0 Precision: 1.0
- 0 Recall: 0.9688
- 0 F1-score: 0.9841
- 0 Support: 32
- 1 Precision: 0.9667
- 1 Recall: 1.0
- 1 F1-score: 0.9831
- 1 Support: 29
- 2 Precision: 1.0
- 2 Recall: 1.0
- 2 F1-score: 1.0
- 2 Support: 29
- 3 Precision: 1.0
- 3 Recall: 1.0
- 3 F1-score: 1.0
- 3 Support: 8
- Accuracy: 0.9898
- Macro avg Precision: 0.9917
- Macro avg Recall: 0.9922
- Macro avg F1-score: 0.9918
- Macro avg Support: 98
- Weighted avg Precision: 0.9901
- Weighted avg Recall: 0.9898
- Weighted avg F1-score: 0.9898
- Weighted avg Support: 98
- Wer: 0.4059
- Mtrix: [[0, 1, 2, 3], [0, 31, 1, 0, 0], [1, 0, 29, 0, 0], [2, 0, 0, 29, 0], [3, 0, 0, 0, 8]]
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 70
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | 0 Precision | 0 Recall | 0 F1-score | 0 Support | 1 Precision | 1 Recall | 1 F1-score | 1 Support | 2 Precision | 2 Recall | 2 F1-score | 2 Support | 3 Precision | 3 Recall | 3 F1-score | 3 Support | Accuracy | Macro avg Precision | Macro avg Recall | Macro avg F1-score | Macro avg Support | Weighted avg Precision | Weighted avg Recall | Weighted avg F1-score | Weighted avg Support | Wer | Mtrix |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1.6359 | 4.16 | 100 | 1.5622 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 29 | 0.2333 | 0.7241 | 0.3529 | 29 | 0.0 | 0.0 | 0.0 | 8 | 0.2143 | 0.0583 | 0.1810 | 0.0882 | 98 | 0.0690 | 0.2143 | 0.1044 | 98 | 0.9761 | [[0, 1, 2, 3], [0, 0, 0, 32, 0], [1, 0, 0, 29, 0], [2, 8, 0, 21, 0], [3, 0, 0, 8, 0]] |
1.4941 | 8.33 | 200 | 1.2550 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 29 | 0.2333 | 0.7241 | 0.3529 | 29 | 0.0 | 0.0 | 0.0 | 8 | 0.2143 | 0.0583 | 0.1810 | 0.0882 | 98 | 0.0690 | 0.2143 | 0.1044 | 98 | 0.9761 | [[0, 1, 2, 3], [0, 0, 0, 32, 0], [1, 0, 0, 29, 0], [2, 8, 0, 21, 0], [3, 0, 0, 8, 0]] |
1.1062 | 12.49 | 300 | 1.1919 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 29 | 0.2333 | 0.7241 | 0.3529 | 29 | 0.0 | 0.0 | 0.0 | 8 | 0.2143 | 0.0583 | 0.1810 | 0.0882 | 98 | 0.0690 | 0.2143 | 0.1044 | 98 | 0.9761 | [[0, 1, 2, 3], [0, 0, 0, 32, 0], [1, 0, 0, 29, 0], [2, 8, 0, 21, 0], [3, 0, 0, 8, 0]] |
1.0287 | 16.65 | 400 | 0.9334 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 29 | 0.2333 | 0.7241 | 0.3529 | 29 | 0.0 | 0.0 | 0.0 | 8 | 0.2143 | 0.0583 | 0.1810 | 0.0882 | 98 | 0.0690 | 0.2143 | 0.1044 | 98 | 0.9761 | [[0, 1, 2, 3], [0, 0, 0, 32, 0], [1, 0, 0, 29, 0], [2, 8, 0, 21, 0], [3, 0, 0, 8, 0]] |
0.9124 | 20.82 | 500 | 0.8485 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 29 | 0.2333 | 0.7241 | 0.3529 | 29 | 0.0 | 0.0 | 0.0 | 8 | 0.2143 | 0.0583 | 0.1810 | 0.0882 | 98 | 0.0690 | 0.2143 | 0.1044 | 98 | 0.9761 | [[0, 1, 2, 3], [0, 0, 0, 32, 0], [1, 0, 0, 29, 0], [2, 8, 0, 21, 0], [3, 0, 0, 8, 0]] |
0.8822 | 24.98 | 600 | 0.9073 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 29 | 0.2333 | 0.7241 | 0.3529 | 29 | 0.0 | 0.0 | 0.0 | 8 | 0.2143 | 0.0583 | 0.1810 | 0.0882 | 98 | 0.0690 | 0.2143 | 0.1044 | 98 | 0.9761 | [[0, 1, 2, 3], [0, 0, 0, 32, 0], [1, 0, 0, 29, 0], [2, 8, 0, 21, 0], [3, 0, 0, 8, 0]] |
0.8117 | 29.16 | 700 | 0.8052 | 1.0 | 0.9375 | 0.9677 | 32 | 0.9062 | 1.0 | 0.9508 | 29 | 1.0 | 0.9655 | 0.9825 | 29 | 1.0 | 1.0 | 1.0 | 8 | 0.9694 | 0.9766 | 0.9758 | 0.9753 | 98 | 0.9723 | 0.9694 | 0.9697 | 98 | 1.0 | [[0, 1, 2, 3], [0, 30, 2, 0, 0], [1, 0, 29, 0, 0], [2, 0, 1, 28, 0], [3, 0, 0, 0, 8]] |
0.7944 | 33.33 | 800 | 0.7554 | 1.0 | 0.9688 | 0.9841 | 32 | 0.9355 | 1.0 | 0.9667 | 29 | 1.0 | 0.9655 | 0.9825 | 29 | 1.0 | 1.0 | 1.0 | 8 | 0.9796 | 0.9839 | 0.9836 | 0.9833 | 98 | 0.9809 | 0.9796 | 0.9798 | 98 | 1.0 | [[0, 1, 2, 3], [0, 31, 1, 0, 0], [1, 0, 29, 0, 0], [2, 0, 1, 28, 0], [3, 0, 0, 0, 8]] |
0.7473 | 37.49 | 900 | 0.7203 | 1.0 | 0.9688 | 0.9841 | 32 | 0.9667 | 1.0 | 0.9831 | 29 | 1.0 | 1.0 | 1.0 | 29 | 1.0 | 1.0 | 1.0 | 8 | 0.9898 | 0.9917 | 0.9922 | 0.9918 | 98 | 0.9901 | 0.9898 | 0.9898 | 98 | 1.0 | [[0, 1, 2, 3], [0, 31, 1, 0, 0], [1, 0, 29, 0, 0], [2, 0, 0, 29, 0], [3, 0, 0, 0, 8]] |
0.3694 | 41.65 | 1000 | 0.3012 | 1.0 | 0.9688 | 0.9841 | 32 | 0.9667 | 1.0 | 0.9831 | 29 | 1.0 | 1.0 | 1.0 | 29 | 1.0 | 1.0 | 1.0 | 8 | 0.9898 | 0.9917 | 0.9922 | 0.9918 | 98 | 0.9901 | 0.9898 | 0.9898 | 98 | 0.6408 | [[0, 1, 2, 3], [0, 31, 1, 0, 0], [1, 0, 29, 0, 0], [2, 0, 0, 29, 0], [3, 0, 0, 0, 8]] |
0.2322 | 45.82 | 1100 | 0.2035 | 1.0 | 0.9688 | 0.9841 | 32 | 0.9667 | 1.0 | 0.9831 | 29 | 1.0 | 1.0 | 1.0 | 29 | 1.0 | 1.0 | 1.0 | 8 | 0.9898 | 0.9917 | 0.9922 | 0.9918 | 98 | 0.9901 | 0.9898 | 0.9898 | 98 | 0.7970 | [[0, 1, 2, 3], [0, 31, 1, 0, 0], [1, 0, 29, 0, 0], [2, 0, 0, 29, 0], [3, 0, 0, 0, 8]] |
0.1993 | 49.98 | 1200 | 0.1834 | 1.0 | 0.9688 | 0.9841 | 32 | 0.9667 | 1.0 | 0.9831 | 29 | 1.0 | 1.0 | 1.0 | 29 | 1.0 | 1.0 | 1.0 | 8 | 0.9898 | 0.9917 | 0.9922 | 0.9918 | 98 | 0.9901 | 0.9898 | 0.9898 | 98 | 0.6420 | [[0, 1, 2, 3], [0, 31, 1, 0, 0], [1, 0, 29, 0, 0], [2, 0, 0, 29, 0], [3, 0, 0, 0, 8]] |
0.2195 | 54.16 | 1300 | 0.1791 | 1.0 | 0.9688 | 0.9841 | 32 | 0.9667 | 1.0 | 0.9831 | 29 | 1.0 | 1.0 | 1.0 | 29 | 1.0 | 1.0 | 1.0 | 8 | 0.9898 | 0.9917 | 0.9922 | 0.9918 | 98 | 0.9901 | 0.9898 | 0.9898 | 98 | 0.7617 | [[0, 1, 2, 3], [0, 31, 1, 0, 0], [1, 0, 29, 0, 0], [2, 0, 0, 29, 0], [3, 0, 0, 0, 8]] |
0.1691 | 58.33 | 1400 | 0.1660 | 1.0 | 0.9688 | 0.9841 | 32 | 0.9667 | 1.0 | 0.9831 | 29 | 1.0 | 1.0 | 1.0 | 29 | 1.0 | 1.0 | 1.0 | 8 | 0.9898 | 0.9917 | 0.9922 | 0.9918 | 98 | 0.9901 | 0.9898 | 0.9898 | 98 | 0.7058 | [[0, 1, 2, 3], [0, 31, 1, 0, 0], [1, 0, 29, 0, 0], [2, 0, 0, 29, 0], [3, 0, 0, 0, 8]] |
0.154 | 62.49 | 1500 | 0.1797 | 1.0 | 0.9688 | 0.9841 | 32 | 0.9667 | 1.0 | 0.9831 | 29 | 1.0 | 1.0 | 1.0 | 29 | 1.0 | 1.0 | 1.0 | 8 | 0.9898 | 0.9917 | 0.9922 | 0.9918 | 98 | 0.9901 | 0.9898 | 0.9898 | 98 | 0.4367 | [[0, 1, 2, 3], [0, 31, 1, 0, 0], [1, 0, 29, 0, 0], [2, 0, 0, 29, 0], [3, 0, 0, 0, 8]] |
0.15 | 66.65 | 1600 | 0.1790 | 1.0 | 0.9688 | 0.9841 | 32 | 0.9667 | 1.0 | 0.9831 | 29 | 1.0 | 1.0 | 1.0 | 29 | 1.0 | 1.0 | 1.0 | 8 | 0.9898 | 0.9917 | 0.9922 | 0.9918 | 98 | 0.9901 | 0.9898 | 0.9898 | 98 | 0.3888 | [[0, 1, 2, 3], [0, 31, 1, 0, 0], [1, 0, 29, 0, 0], [2, 0, 0, 29, 0], [3, 0, 0, 0, 8]] |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2