<!-- 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-dt-oversampling-duplicate
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: 0.8784
- Accuracy: 0.7464
- F1: 0.7463
- Precision: 0.7490
- Recall: 0.7464
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 |
---|---|---|---|---|---|---|---|
1.0426 | 1.0 | 313 | 1.0713 | 0.5496 | 0.5029 | 0.5438 | 0.5496 |
0.7673 | 2.0 | 626 | 0.7795 | 0.6696 | 0.6601 | 0.6617 | 0.6696 |
0.4519 | 3.0 | 939 | 0.8386 | 0.6968 | 0.6936 | 0.6990 | 0.6968 |
0.2095 | 4.0 | 1252 | 1.0060 | 0.7392 | 0.7388 | 0.7389 | 0.7392 |
0.1659 | 5.0 | 1565 | 1.1480 | 0.7384 | 0.7386 | 0.7397 | 0.7384 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3