malay_dataset_checkpoint
This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5938
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: 1e-05
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.8835 | 0.17 | 500 | 1.1947 |
1.156 | 0.34 | 1000 | 0.9847 |
1.0174 | 0.51 | 1500 | 0.8688 |
0.9117 | 0.68 | 2000 | 0.7840 |
0.8413 | 0.86 | 2500 | 0.7218 |
0.8081 | 1.03 | 3000 | 0.7093 |
0.7662 | 1.2 | 3500 | 0.6677 |
0.746 | 1.37 | 4000 | 0.6525 |
0.7318 | 1.54 | 4500 | 0.6492 |
0.7043 | 1.71 | 5000 | 0.6472 |
0.7157 | 1.88 | 5500 | 0.6153 |
0.6821 | 2.05 | 6000 | 0.6070 |
0.692 | 2.23 | 6500 | 0.6133 |
0.671 | 2.4 | 7000 | 0.6089 |
0.6676 | 2.57 | 7500 | 0.6000 |
0.6769 | 2.74 | 8000 | 0.5956 |
0.6612 | 2.91 | 8500 | 0.5938 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1