<!-- 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_onSet1
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: 0.1815
- 0 Precision: 1.0
- 0 Recall: 0.9677
- 0 F1-score: 0.9836
- 0 Support: 31
- 1 Precision: 0.9545
- 1 Recall: 1.0
- 1 F1-score: 0.9767
- 1 Support: 21
- 2 Precision: 1.0
- 2 Recall: 1.0
- 2 F1-score: 1.0
- 2 Support: 30
- 3 Precision: 1.0
- 3 Recall: 1.0
- 3 F1-score: 1.0
- 3 Support: 16
- Accuracy: 0.9898
- Macro avg Precision: 0.9886
- Macro avg Recall: 0.9919
- Macro avg F1-score: 0.9901
- Macro avg Support: 98
- Weighted avg Precision: 0.9903
- Weighted avg Recall: 0.9898
- Weighted avg F1-score: 0.9898
- Weighted avg Support: 98
- Wer: 0.7883
- Mtrix: [[0, 1, 2, 3], [0, 30, 1, 0, 0], [1, 0, 21, 0, 0], [2, 0, 0, 30, 0], [3, 0, 0, 0, 16]]
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1.6949 | 4.16 | 100 | 1.6177 | 1.0 | 0.2581 | 0.4103 | 31 | 0.0 | 0.0 | 0.0 | 21 | 0.3333 | 1.0 | 0.5 | 30 | 0.0 | 0.0 | 0.0 | 16 | 0.3878 | 0.3333 | 0.3145 | 0.2276 | 98 | 0.4184 | 0.3878 | 0.2828 | 98 | 0.9655 | [[0, 1, 2, 3], [0, 8, 0, 23, 0], [1, 0, 0, 21, 0], [2, 0, 0, 30, 0], [3, 0, 0, 16, 0]] |
1.5778 | 8.33 | 200 | 1.3535 | 1.0 | 0.2581 | 0.4103 | 31 | 0.0 | 0.0 | 0.0 | 21 | 0.3333 | 1.0 | 0.5 | 30 | 0.0 | 0.0 | 0.0 | 16 | 0.3878 | 0.3333 | 0.3145 | 0.2276 | 98 | 0.4184 | 0.3878 | 0.2828 | 98 | 0.9655 | [[0, 1, 2, 3], [0, 8, 0, 23, 0], [1, 0, 0, 21, 0], [2, 0, 0, 30, 0], [3, 0, 0, 16, 0]] |
1.2861 | 12.49 | 300 | 1.0938 | 1.0 | 0.2581 | 0.4103 | 31 | 0.0 | 0.0 | 0.0 | 21 | 0.3333 | 1.0 | 0.5 | 30 | 0.0 | 0.0 | 0.0 | 16 | 0.3878 | 0.3333 | 0.3145 | 0.2276 | 98 | 0.4184 | 0.3878 | 0.2828 | 98 | 0.9655 | [[0, 1, 2, 3], [0, 8, 0, 23, 0], [1, 0, 0, 21, 0], [2, 0, 0, 30, 0], [3, 0, 0, 16, 0]] |
0.954 | 16.65 | 400 | 0.9480 | 1.0 | 0.2581 | 0.4103 | 31 | 0.0 | 0.0 | 0.0 | 21 | 0.3333 | 1.0 | 0.5 | 30 | 0.0 | 0.0 | 0.0 | 16 | 0.3878 | 0.3333 | 0.3145 | 0.2276 | 98 | 0.4184 | 0.3878 | 0.2828 | 98 | 0.9655 | [[0, 1, 2, 3], [0, 8, 0, 23, 0], [1, 0, 0, 21, 0], [2, 0, 0, 30, 0], [3, 0, 0, 16, 0]] |
0.8849 | 20.82 | 500 | 0.9231 | 1.0 | 0.2581 | 0.4103 | 31 | 0.0 | 0.0 | 0.0 | 21 | 0.3333 | 1.0 | 0.5 | 30 | 0.0 | 0.0 | 0.0 | 16 | 0.3878 | 0.3333 | 0.3145 | 0.2276 | 98 | 0.4184 | 0.3878 | 0.2828 | 98 | 0.9655 | [[0, 1, 2, 3], [0, 8, 0, 23, 0], [1, 0, 0, 21, 0], [2, 0, 0, 30, 0], [3, 0, 0, 16, 0]] |
0.8674 | 24.98 | 600 | 0.8767 | 1.0 | 0.2581 | 0.4103 | 31 | 0.0 | 0.0 | 0.0 | 21 | 0.3333 | 1.0 | 0.5 | 30 | 0.0 | 0.0 | 0.0 | 16 | 0.3878 | 0.3333 | 0.3145 | 0.2276 | 98 | 0.4184 | 0.3878 | 0.2828 | 98 | 0.9655 | [[0, 1, 2, 3], [0, 8, 0, 23, 0], [1, 0, 0, 21, 0], [2, 0, 0, 30, 0], [3, 0, 0, 16, 0]] |
0.7921 | 29.16 | 700 | 0.7519 | 1.0 | 0.9677 | 0.9836 | 31 | 0.9545 | 1.0 | 0.9767 | 21 | 1.0 | 1.0 | 1.0 | 30 | 1.0 | 1.0 | 1.0 | 16 | 0.9898 | 0.9886 | 0.9919 | 0.9901 | 98 | 0.9903 | 0.9898 | 0.9898 | 98 | 1.0 | [[0, 1, 2, 3], [0, 30, 1, 0, 0], [1, 0, 21, 0, 0], [2, 0, 0, 30, 0], [3, 0, 0, 0, 16]] |
0.7851 | 33.33 | 800 | 0.8212 | 1.0 | 0.9032 | 0.9492 | 31 | 0.84 | 1.0 | 0.9130 | 21 | 1.0 | 1.0 | 1.0 | 30 | 1.0 | 0.9375 | 0.9677 | 16 | 0.9592 | 0.96 | 0.9602 | 0.9575 | 98 | 0.9657 | 0.9592 | 0.9600 | 98 | 1.0 | [[0, 1, 2, 3], [0, 28, 3, 0, 0], [1, 0, 21, 0, 0], [2, 0, 0, 30, 0], [3, 0, 1, 0, 15]] |
0.7657 | 37.49 | 900 | 0.7504 | 1.0 | 0.9677 | 0.9836 | 31 | 0.9130 | 1.0 | 0.9545 | 21 | 1.0 | 1.0 | 1.0 | 30 | 1.0 | 0.9375 | 0.9677 | 16 | 0.9796 | 0.9783 | 0.9763 | 0.9765 | 98 | 0.9814 | 0.9796 | 0.9798 | 98 | 1.0 | [[0, 1, 2, 3], [0, 30, 1, 0, 0], [1, 0, 21, 0, 0], [2, 0, 0, 30, 0], [3, 0, 1, 0, 15]] |
0.688 | 41.65 | 1000 | 0.6897 | 1.0 | 1.0 | 1.0 | 31 | 0.9130 | 1.0 | 0.9545 | 21 | 1.0 | 0.9667 | 0.9831 | 30 | 1.0 | 0.9375 | 0.9677 | 16 | 0.9796 | 0.9783 | 0.9760 | 0.9763 | 98 | 0.9814 | 0.9796 | 0.9798 | 98 | 0.7008 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 21, 0, 0], [2, 0, 1, 29, 0], [3, 0, 1, 0, 15]] |
0.4415 | 45.82 | 1100 | 0.1917 | 1.0 | 1.0 | 1.0 | 31 | 1.0 | 1.0 | 1.0 | 21 | 1.0 | 1.0 | 1.0 | 30 | 1.0 | 1.0 | 1.0 | 16 | 1.0 | 1.0 | 1.0 | 1.0 | 98 | 1.0 | 1.0 | 1.0 | 98 | 0.6974 | [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 21, 0, 0], [2, 0, 0, 30, 0], [3, 0, 0, 0, 16]] |
0.3074 | 49.98 | 1200 | 0.1865 | 1.0 | 0.9677 | 0.9836 | 31 | 0.9545 | 1.0 | 0.9767 | 21 | 1.0 | 1.0 | 1.0 | 30 | 1.0 | 1.0 | 1.0 | 16 | 0.9898 | 0.9886 | 0.9919 | 0.9901 | 98 | 0.9903 | 0.9898 | 0.9898 | 98 | 0.6686 | [[0, 1, 2, 3], [0, 30, 1, 0, 0], [1, 0, 21, 0, 0], [2, 0, 0, 30, 0], [3, 0, 0, 0, 16]] |
0.2069 | 54.16 | 1300 | 0.1821 | 1.0 | 0.9677 | 0.9836 | 31 | 0.9545 | 1.0 | 0.9767 | 21 | 1.0 | 1.0 | 1.0 | 30 | 1.0 | 1.0 | 1.0 | 16 | 0.9898 | 0.9886 | 0.9919 | 0.9901 | 98 | 0.9903 | 0.9898 | 0.9898 | 98 | 0.7043 | [[0, 1, 2, 3], [0, 30, 1, 0, 0], [1, 0, 21, 0, 0], [2, 0, 0, 30, 0], [3, 0, 0, 0, 16]] |
0.1791 | 58.33 | 1400 | 0.1866 | 1.0 | 0.9677 | 0.9836 | 31 | 0.9130 | 1.0 | 0.9545 | 21 | 1.0 | 0.9667 | 0.9831 | 30 | 1.0 | 1.0 | 1.0 | 16 | 0.9796 | 0.9783 | 0.9836 | 0.9803 | 98 | 0.9814 | 0.9796 | 0.9799 | 98 | 0.6893 | [[0, 1, 2, 3], [0, 30, 1, 0, 0], [1, 0, 21, 0, 0], [2, 0, 1, 29, 0], [3, 0, 0, 0, 16]] |
0.1717 | 62.49 | 1500 | 0.1839 | 1.0 | 0.9677 | 0.9836 | 31 | 0.9545 | 1.0 | 0.9767 | 21 | 1.0 | 1.0 | 1.0 | 30 | 1.0 | 1.0 | 1.0 | 16 | 0.9898 | 0.9886 | 0.9919 | 0.9901 | 98 | 0.9903 | 0.9898 | 0.9898 | 98 | 0.7848 | [[0, 1, 2, 3], [0, 30, 1, 0, 0], [1, 0, 21, 0, 0], [2, 0, 0, 30, 0], [3, 0, 0, 0, 16]] |
0.1571 | 66.65 | 1600 | 0.1799 | 1.0 | 0.9677 | 0.9836 | 31 | 0.9545 | 1.0 | 0.9767 | 21 | 1.0 | 1.0 | 1.0 | 30 | 1.0 | 1.0 | 1.0 | 16 | 0.9898 | 0.9886 | 0.9919 | 0.9901 | 98 | 0.9903 | 0.9898 | 0.9898 | 98 | 0.7929 | [[0, 1, 2, 3], [0, 30, 1, 0, 0], [1, 0, 21, 0, 0], [2, 0, 0, 30, 0], [3, 0, 0, 0, 16]] |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2