<!-- 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-real
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: 1.0733
- Accuracy: 0.684
- F1: 0.6768
- Precision: 0.6727
- Recall: 0.684
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 |
---|---|---|---|---|---|---|---|
0.939 | 1.0 | 313 | 0.9081 | 0.6268 | 0.5698 | 0.6363 | 0.6268 |
0.83 | 2.0 | 626 | 0.7514 | 0.664 | 0.6410 | 0.6418 | 0.664 |
0.6184 | 3.0 | 939 | 0.8578 | 0.6484 | 0.6502 | 0.6529 | 0.6484 |
0.1805 | 4.0 | 1252 | 1.0733 | 0.684 | 0.6768 | 0.6727 | 0.684 |
0.3776 | 5.0 | 1565 | 1.3549 | 0.6672 | 0.6646 | 0.6630 | 0.6672 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3