speecht5_finetuned_voxpopuli_nl
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: 0.6134
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6458 | 0.99 | 64 | 1.2831 |
| 1.2834 | 2.0 | 129 | 1.0777 |
| 1.0903 | 2.99 | 193 | 0.8623 |
| 0.8942 | 4.0 | 258 | 0.7390 |
| 0.8074 | 4.99 | 322 | 0.6889 |
| 0.757 | 6.0 | 387 | 0.6599 |
| 0.7273 | 6.99 | 451 | 0.6408 |
| 0.6902 | 8.0 | 516 | 0.6291 |
| 0.6832 | 8.99 | 580 | 0.6157 |
| 0.6657 | 9.92 | 640 | 0.6134 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.0+cu117
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for renad01/speecht5_finetuned_voxpopuli_nl
Base model
microsoft/speecht5_tts