speecht5_tts_sinhala
This model is a fine-tuned version of microsoft/speecht5_tts on the sinhala_tts dataset. It achieves the following results on the evaluation set:
- Loss: 0.4122
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4719 | 28.17 | 1000 | 0.4329 |
| 0.4419 | 56.34 | 2000 | 0.4149 |
| 0.4281 | 84.51 | 3000 | 0.4132 |
| 0.4358 | 112.68 | 4000 | 0.4122 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.16.0
- Tokenizers 0.15.0