<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
wav2vec2-xlsr-ravdess-speech-emotion-recognition-new
This model is a fine-tuned version of lighteternal/wav2vec2-large-xlsr-53-greek on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8209
- Accuracy: 0.625
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: 0.0001
- 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: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.1484 | 0.42 | 10 | 1.1682 | 0.4375 |
1.1195 | 0.83 | 20 | 1.0696 | 0.5417 |
0.9414 | 1.25 | 30 | 1.0196 | 0.5 |
0.8109 | 1.67 | 40 | 0.7216 | 0.6875 |
0.724 | 2.08 | 50 | 0.7667 | 0.6875 |
0.6081 | 2.5 | 60 | 0.7912 | 0.6458 |
0.6073 | 2.92 | 70 | 0.8209 | 0.625 |
Framework versions
- Transformers 4.23.0.dev0
- Pytorch 1.12.1+cu102
- Datasets 2.4.1.dev0
- Tokenizers 0.12.1