<!-- 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_onSet3
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: 0.1590
- 0 Precision: 0.9688
- 0 Recall: 1.0
- 0 F1-score: 0.9841
- 0 Support: 31
- 1 Precision: 1.0
- 1 Recall: 1.0
- 1 F1-score: 1.0
- 1 Support: 25
- 2 Precision: 1.0
- 2 Recall: 0.9474
- 2 F1-score: 0.9730
- 2 Support: 19
- 3 Precision: 0.9545
- 3 Recall: 0.9545
- 3 F1-score: 0.9545
- 3 Support: 22
- Accuracy: 0.9794
- Macro avg Precision: 0.9808
- Macro avg Recall: 0.9755
- Macro avg F1-score: 0.9779
- Macro avg Support: 97
- Weighted avg Precision: 0.9797
- Weighted avg Recall: 0.9794
- Weighted avg F1-score: 0.9793
- Weighted avg Support: 97
- Wer: 0.2202
- Mtrix: [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 0, 18, 1], [3, 1, 0, 0, 21]]
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1.642 | 4.16 | 100 | 1.5891 | 1.0 | 0.2581 | 0.4103 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.2135 | 1.0 | 0.3519 | 19 | 0.0 | 0.0 | 0.0 | 22 | 0.2784 | 0.3034 | 0.3145 | 0.1905 | 97 | 0.3614 | 0.2784 | 0.2000 | 97 | 0.9780 | [[0, 1, 2, 3], [0, 8, 0, 23, 0], [1, 0, 0, 25, 0], [2, 0, 0, 19, 0], [3, 0, 0, 22, 0]] |
1.4791 | 8.33 | 200 | 1.3227 | 1.0 | 0.2581 | 0.4103 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.2135 | 1.0 | 0.3519 | 19 | 0.0 | 0.0 | 0.0 | 22 | 0.2784 | 0.3034 | 0.3145 | 0.1905 | 97 | 0.3614 | 0.2784 | 0.2000 | 97 | 0.9780 | [[0, 1, 2, 3], [0, 8, 0, 23, 0], [1, 0, 0, 25, 0], [2, 0, 0, 19, 0], [3, 0, 0, 22, 0]] |
1.2376 | 12.49 | 300 | 1.0446 | 1.0 | 0.2581 | 0.4103 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.2135 | 1.0 | 0.3519 | 19 | 0.0 | 0.0 | 0.0 | 22 | 0.2784 | 0.3034 | 0.3145 | 0.1905 | 97 | 0.3614 | 0.2784 | 0.2000 | 97 | 0.9780 | [[0, 1, 2, 3], [0, 8, 0, 23, 0], [1, 0, 0, 25, 0], [2, 0, 0, 19, 0], [3, 0, 0, 22, 0]] |
0.9622 | 16.65 | 400 | 0.8811 | 1.0 | 0.2581 | 0.4103 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.2135 | 1.0 | 0.3519 | 19 | 0.0 | 0.0 | 0.0 | 22 | 0.2784 | 0.3034 | 0.3145 | 0.1905 | 97 | 0.3614 | 0.2784 | 0.2000 | 97 | 0.9780 | [[0, 1, 2, 3], [0, 8, 0, 23, 0], [1, 0, 0, 25, 0], [2, 0, 0, 19, 0], [3, 0, 0, 22, 0]] |
0.8614 | 20.82 | 500 | 0.8174 | 1.0 | 0.2581 | 0.4103 | 31 | 0.0 | 0.0 | 0.0 | 25 | 0.2135 | 1.0 | 0.3519 | 19 | 0.0 | 0.0 | 0.0 | 22 | 0.2784 | 0.3034 | 0.3145 | 0.1905 | 97 | 0.3614 | 0.2784 | 0.2000 | 97 | 0.9780 | [[0, 1, 2, 3], [0, 8, 0, 23, 0], [1, 0, 0, 25, 0], [2, 0, 0, 19, 0], [3, 0, 0, 22, 0]] |
0.8344 | 24.98 | 600 | 0.7498 | 1.0 | 1.0 | 1.0 | 31 | 1.0 | 1.0 | 1.0 | 25 | 1.0 | 1.0 | 1.0 | 19 | 1.0 | 1.0 | 1.0 | 22 | 1.0 | 1.0 | 1.0 | 1.0 | 97 | 1.0 | 1.0 | 1.0 | 97 | 1.0 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 0, 19, 0], [3, 0, 0, 0, 22]] |
0.8105 | 29.16 | 700 | 0.7907 | 0.9688 | 1.0 | 0.9841 | 31 | 1.0 | 0.96 | 0.9796 | 25 | 0.95 | 1.0 | 0.9744 | 19 | 1.0 | 0.9545 | 0.9767 | 22 | 0.9794 | 0.9797 | 0.9786 | 0.9787 | 97 | 0.9802 | 0.9794 | 0.9794 | 97 | 1.0 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 24, 1, 0], [2, 0, 0, 19, 0], [3, 1, 0, 0, 21]] |
0.6168 | 33.33 | 800 | 0.5496 | 0.9688 | 1.0 | 0.9841 | 31 | 1.0 | 0.96 | 0.9796 | 25 | 0.95 | 1.0 | 0.9744 | 19 | 1.0 | 0.9545 | 0.9767 | 22 | 0.9794 | 0.9797 | 0.9786 | 0.9787 | 97 | 0.9802 | 0.9794 | 0.9794 | 97 | 0.5840 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 24, 1, 0], [2, 0, 0, 19, 0], [3, 1, 0, 0, 21]] |
0.2701 | 37.49 | 900 | 0.2587 | 1.0 | 1.0 | 1.0 | 31 | 1.0 | 0.96 | 0.9796 | 25 | 0.9474 | 0.9474 | 0.9474 | 19 | 0.9565 | 1.0 | 0.9778 | 22 | 0.9794 | 0.9760 | 0.9768 | 0.9762 | 97 | 0.9798 | 0.9794 | 0.9794 | 97 | 0.2375 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 24, 1, 0], [2, 0, 0, 18, 1], [3, 0, 0, 0, 22]] |
0.1745 | 41.65 | 1000 | 0.2219 | 0.9688 | 1.0 | 0.9841 | 31 | 1.0 | 1.0 | 1.0 | 25 | 1.0 | 0.9474 | 0.9730 | 19 | 0.9545 | 0.9545 | 0.9545 | 22 | 0.9794 | 0.9808 | 0.9755 | 0.9779 | 97 | 0.9797 | 0.9794 | 0.9793 | 97 | 0.2445 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 0, 18, 1], [3, 1, 0, 0, 21]] |
0.1494 | 45.82 | 1100 | 0.2548 | 0.9688 | 1.0 | 0.9841 | 31 | 1.0 | 0.96 | 0.9796 | 25 | 1.0 | 0.9474 | 0.9730 | 19 | 0.9130 | 0.9545 | 0.9333 | 22 | 0.9691 | 0.9704 | 0.9655 | 0.9675 | 97 | 0.9703 | 0.9691 | 0.9693 | 97 | 0.2352 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 24, 0, 1], [2, 0, 0, 18, 1], [3, 1, 0, 0, 21]] |
0.1213 | 49.98 | 1200 | 0.1756 | 0.9688 | 1.0 | 0.9841 | 31 | 0.9615 | 1.0 | 0.9804 | 25 | 1.0 | 0.9474 | 0.9730 | 19 | 1.0 | 0.9545 | 0.9767 | 22 | 0.9794 | 0.9826 | 0.9755 | 0.9786 | 97 | 0.9801 | 0.9794 | 0.9793 | 97 | 0.2260 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 1, 18, 0], [3, 1, 0, 0, 21]] |
0.0964 | 54.16 | 1300 | 0.1884 | 0.9688 | 1.0 | 0.9841 | 31 | 1.0 | 1.0 | 1.0 | 25 | 1.0 | 0.9474 | 0.9730 | 19 | 0.9545 | 0.9545 | 0.9545 | 22 | 0.9794 | 0.9808 | 0.9755 | 0.9779 | 97 | 0.9797 | 0.9794 | 0.9793 | 97 | 0.2260 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 0, 18, 1], [3, 1, 0, 0, 21]] |
0.0859 | 58.33 | 1400 | 0.1212 | 0.9688 | 1.0 | 0.9841 | 31 | 1.0 | 1.0 | 1.0 | 25 | 1.0 | 1.0 | 1.0 | 19 | 1.0 | 0.9545 | 0.9767 | 22 | 0.9897 | 0.9922 | 0.9886 | 0.9902 | 97 | 0.9900 | 0.9897 | 0.9897 | 97 | 0.2202 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 0, 19, 0], [3, 1, 0, 0, 21]] |
0.0845 | 62.49 | 1500 | 0.1254 | 0.9688 | 1.0 | 0.9841 | 31 | 1.0 | 1.0 | 1.0 | 25 | 1.0 | 1.0 | 1.0 | 19 | 1.0 | 0.9545 | 0.9767 | 22 | 0.9897 | 0.9922 | 0.9886 | 0.9902 | 97 | 0.9900 | 0.9897 | 0.9897 | 97 | 0.2178 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 0, 19, 0], [3, 1, 0, 0, 21]] |
0.0831 | 66.65 | 1600 | 0.1590 | 0.9688 | 1.0 | 0.9841 | 31 | 1.0 | 1.0 | 1.0 | 25 | 1.0 | 0.9474 | 0.9730 | 19 | 0.9545 | 0.9545 | 0.9545 | 22 | 0.9794 | 0.9808 | 0.9755 | 0.9779 | 97 | 0.9797 | 0.9794 | 0.9793 | 97 | 0.2202 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 0, 18, 1], [3, 1, 0, 0, 21]] |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2