wav2vec2-speech-emotion-recognition
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: 0.6216
- Accuracy: 0.7701
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
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4442 | 1.0 | 97 | 1.3949 | 0.4483 |
| 1.0681 | 2.0 | 194 | 1.0663 | 0.5517 |
| 0.9145 | 3.0 | 291 | 0.9559 | 0.6092 |
| 0.7983 | 4.0 | 388 | 0.8588 | 0.6207 |
| 0.6426 | 5.0 | 485 | 0.7349 | 0.6782 |
| 0.5086 | 6.0 | 582 | 0.6216 | 0.7701 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3