wav2vec2-4datasets-allgender
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: 0.7385
- Accuracy: 0.8400
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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 |
|---|---|---|---|---|
| 0.8667 | 1.0 | 1197 | 0.9470 | 0.6750 |
| 0.5989 | 2.0 | 2394 | 0.6872 | 0.7736 |
| 0.5797 | 3.0 | 3591 | 0.6329 | 0.8162 |
| 0.176 | 4.0 | 4788 | 0.7188 | 0.8317 |
| 0.1353 | 5.0 | 5985 | 0.7385 | 0.8400 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.18.0
- Tokenizers 0.13.3