<!-- 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. -->
wav2vec2-large-xlsr-53-english-pronunciation-evaluation-bs-v4
This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-english on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3181
- Accuracy: 0.79
- F1: 0.7920
- Precision: 0.7954
- Recall: 0.79
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
1.14 | 1.0 | 2000 | 0.9878 | 0.604 | 0.5956 | 0.6041 | 0.604 |
1.3551 | 2.0 | 4000 | 1.0238 | 0.636 | 0.6261 | 0.6489 | 0.636 |
0.7984 | 3.0 | 6000 | 1.0629 | 0.748 | 0.7475 | 0.7494 | 0.748 |
0.6879 | 4.0 | 8000 | 1.2007 | 0.772 | 0.7733 | 0.7750 | 0.772 |
0.0593 | 5.0 | 10000 | 1.2298 | 0.796 | 0.7979 | 0.8011 | 0.796 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3