SpeechT5 TTS Finnish
This model is a fine-tuned version of microsoft/speecht5_tts on the VoxPopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.4953
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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|
| 5.9101 | 1.0 | 50 | 0.6594 |
| 5.5265 | 2.0 | 100 | 0.6225 |
| 5.2789 | 3.0 | 150 | 0.5963 |
| 5.0550 | 4.0 | 200 | 0.5794 |
| 4.9240 | 5.0 | 250 | 0.5650 |
| 4.7639 | 6.0 | 300 | 0.5397 |
| 4.5392 | 7.0 | 350 | 0.5169 |
| 4.3294 | 8.0 | 400 | 0.5050 |
| 4.2417 | 9.0 | 450 | 0.5019 |
| 4.2179 | 10.0 | 500 | 0.4953 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2