<!-- 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-dp-70-15-15
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: 1.0328
- Accuracy: 0.7827
- F1: 0.7812
- Precision: 0.7819
- Recall: 0.7827
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: 8
- eval_batch_size: 8
- 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 |
---|---|---|---|---|---|---|---|
0.7945 | 1.0 | 438 | 0.8709 | 0.5573 | 0.5239 | 0.5859 | 0.5573 |
0.8011 | 2.0 | 876 | 0.7536 | 0.6533 | 0.6340 | 0.6534 | 0.6533 |
0.6528 | 3.0 | 1314 | 0.6918 | 0.732 | 0.7295 | 0.7313 | 0.732 |
0.3574 | 4.0 | 1752 | 0.8670 | 0.7573 | 0.7540 | 0.7552 | 0.7573 |
0.0999 | 5.0 | 2190 | 1.0217 | 0.7627 | 0.7585 | 0.7619 | 0.7627 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3