<!-- 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-aod-cut-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: 1.0403
- Accuracy: 0.744
- F1: 0.7432
- Precision: 0.7436
- Recall: 0.744
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 |
---|---|---|---|---|---|---|---|
0.8567 | 1.0 | 313 | 0.9539 | 0.5388 | 0.5159 | 0.5387 | 0.5388 |
0.665 | 2.0 | 626 | 0.7520 | 0.6512 | 0.6545 | 0.6625 | 0.6512 |
0.629 | 3.0 | 939 | 0.7775 | 0.7008 | 0.6980 | 0.6978 | 0.7008 |
0.4793 | 4.0 | 1252 | 0.8696 | 0.7268 | 0.7295 | 0.7365 | 0.7268 |
0.2273 | 5.0 | 1565 | 1.0403 | 0.744 | 0.7432 | 0.7436 | 0.744 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3