speecht5_tts_common_voice_uk
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
| 0.4646 |
1.0 |
146 |
0.4160 |
| 0.468 |
2.0 |
292 |
0.4173 |
| 0.4623 |
3.0 |
438 |
0.4177 |
| 0.4637 |
4.0 |
584 |
0.4116 |
| 0.4584 |
5.0 |
730 |
0.4074 |
| 0.4525 |
6.0 |
876 |
0.4074 |
| 0.4438 |
7.0 |
1022 |
0.4054 |
| 0.4433 |
8.0 |
1168 |
0.4020 |
| 0.4401 |
9.0 |
1314 |
0.4018 |
| 0.4401 |
10.0 |
1460 |
0.4015 |
Framework versions
- Transformers 4.37.2
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.15.2
