SpeechT5 TTS Dutch for Prac
This model is a fine-tuned version of [microsoft/speecht5_tts & YC](https://huggingface.co/microsoft/speecht5_tts & YC) on the VoxPopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.4550
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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.522 | 4.3 | 1000 | 0.4755 |
| 0.5028 | 8.6 | 2000 | 0.4618 |
| 0.498 | 12.9 | 3000 | 0.4575 |
| 0.4952 | 17.2 | 4000 | 0.4550 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3