results
This model is a fine-tuned version of facebook/wav2vec2-base on the speech-emotion-recognition-en dataset. It achieves the following results on the evaluation set:
- Loss: 0.7358
- Accuracy: 0.8338
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8199 | 1.0 | 1161 | 0.7154 | 0.7446 |
| 0.7633 | 2.0 | 2322 | 0.5800 | 0.8019 |
| 0.5081 | 3.0 | 3483 | 0.5602 | 0.8084 |
| 0.3336 | 4.0 | 4644 | 0.6145 | 0.8277 |
| 0.3169 | 5.0 | 5805 | 0.6933 | 0.8316 |
| 0.1281 | 6.0 | 6966 | 0.7358 | 0.8338 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1
- Downloads last month
- 5
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for HaniaRuby/speech-emotion-recognition-wav2vec2
Base model
facebook/wav2vec2-base