wav2vec2-base-finetuned-coscan-age_group
This model is a fine-tuned version of facebook/wav2vec2-base on the coscan-speech dataset (age_group).
It achieves the following results on the evaluation set:
- Loss: 0.0118
- Accuracy: 0.9984
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.3669 | 1.0 | 6644 | 0.1547 | 0.9449 |
| 0.0662 | 2.0 | 13288 | 0.0980 | 0.9807 |
| 0.0512 | 3.0 | 19932 | 0.0504 | 0.9911 |
| 0.0008 | 4.0 | 26576 | 0.0302 | 0.9955 |
| 0.0 | 5.0 | 33220 | 0.0118 | 0.9984 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.10.1+cu102
- Datasets 2.4.0
- Tokenizers 0.12.1