<!-- 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-50-25-25
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: 1.0302
- Accuracy: 0.7352
- F1: 0.7332
- Precision: 0.7344
- Recall: 0.7352
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 |
---|---|---|---|---|---|---|---|
0.9734 | 1.0 | 313 | 0.8725 | 0.5952 | 0.5785 | 0.5881 | 0.5952 |
0.8059 | 2.0 | 626 | 0.8028 | 0.6344 | 0.6194 | 0.6234 | 0.6344 |
0.5182 | 3.0 | 939 | 0.8439 | 0.6696 | 0.6544 | 0.6712 | 0.6696 |
0.4905 | 4.0 | 1252 | 0.8330 | 0.7408 | 0.7426 | 0.7467 | 0.7408 |
0.1625 | 5.0 | 1565 | 1.0107 | 0.7496 | 0.7488 | 0.7519 | 0.7496 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3