<!-- 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-augmented
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: 0.8966
- Accuracy: 0.7608
- F1: 0.7592
- Precision: 0.7591
- Recall: 0.7608
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 |
---|---|---|---|---|---|---|---|
1.0067 | 1.0 | 313 | 1.0838 | 0.4368 | 0.3815 | 0.4622 | 0.4368 |
0.6538 | 2.0 | 626 | 1.1189 | 0.532 | 0.4887 | 0.5314 | 0.532 |
0.5285 | 3.0 | 939 | 0.6705 | 0.7184 | 0.7150 | 0.7153 | 0.7184 |
0.396 | 4.0 | 1252 | 0.7915 | 0.7416 | 0.7374 | 0.7397 | 0.7416 |
0.1296 | 5.0 | 1565 | 0.9171 | 0.7592 | 0.7565 | 0.7569 | 0.7592 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3