<!-- 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-60-20-20
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: 0.9015
- Accuracy: 0.743
- F1: 0.7432
- Precision: 0.7495
- Recall: 0.743
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 |
---|---|---|---|---|---|---|---|
0.8727 | 1.0 | 375 | 0.8777 | 0.574 | 0.5558 | 0.5611 | 0.574 |
0.834 | 2.0 | 750 | 0.8086 | 0.652 | 0.6470 | 0.6558 | 0.652 |
0.6609 | 3.0 | 1125 | 0.8289 | 0.695 | 0.6926 | 0.6945 | 0.695 |
0.329 | 4.0 | 1500 | 0.9585 | 0.755 | 0.7558 | 0.7607 | 0.755 |
0.1628 | 5.0 | 1875 | 1.1191 | 0.751 | 0.7488 | 0.7479 | 0.751 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3