wav2vec2-adult-child-cls
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1713
- Accuracy: 0.9460
- F1: 0.9509
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|---|
| 0.323 | 1.0 | 96 | 0.2699 | 0.9026 | 0.9085 |
| 0.2003 | 2.0 | 192 | 0.2005 | 0.9234 | 0.9300 |
| 0.1808 | 3.0 | 288 | 0.1780 | 0.9377 | 0.9438 |
| 0.1537 | 4.0 | 384 | 0.1673 | 0.9441 | 0.9488 |
| 0.1135 | 5.0 | 480 | 0.1713 | 0.9460 | 0.9509 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2+cu102
- Datasets 1.18.3
- Tokenizers 0.10.3