<!-- 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-lr-v4
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: 0.7777
- Accuracy: 0.656
- F1: 0.6292
- Precision: 0.6618
- Recall: 0.656
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: 1e-05
- 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 |
---|---|---|---|---|---|---|---|
0.9582 | 1.0 | 500 | 0.9629 | 0.544 | 0.4585 | 0.5657 | 0.544 |
0.8052 | 2.0 | 1000 | 0.8512 | 0.624 | 0.5916 | 0.6247 | 0.624 |
0.8939 | 3.0 | 1500 | 0.8313 | 0.638 | 0.6071 | 0.6384 | 0.638 |
0.6153 | 4.0 | 2000 | 0.8035 | 0.67 | 0.6442 | 0.6833 | 0.67 |
0.5782 | 5.0 | 2500 | 0.8024 | 0.67 | 0.6458 | 0.6788 | 0.67 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3