SpeechT5 TTS Dutch dec 20
This model is a fine-tuned version of microsoft/speecht5_tts on the procit008/STT_Datasetfacebookfemale dataset. It achieves the following results on the evaluation set:
- Loss: 0.4712
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: Use adamw_torch 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
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0563 | 11.7647 | 1000 | 0.4868 |
| 0.9833 | 23.5294 | 2000 | 0.4746 |
| 0.996 | 35.2941 | 3000 | 0.4736 |
| 0.9925 | 47.0588 | 4000 | 0.4712 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0