SpeechT5 Dutch TTS
This model is a fine-tuned version of microsoft/speecht5_tts on the VoxPopuli (nl subset) dataset. It achieves the following results on the evaluation set:
- Loss: 0.5033
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1558 | 8.0 | 200 | 0.5356 |
| 1.0637 | 16.0 | 400 | 0.5131 |
| 1.0535 | 24.0 | 600 | 0.5042 |
| 1.0114 | 32.0 | 800 | 0.5042 |
| 1.0154 | 40.0 | 1000 | 0.5033 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 48
Model tree for tomragus/speecht5_finetuned_voxpopuli_nl
Base model
microsoft/speecht5_tts