<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
SpeechT5 TTS Hrvatski
This model is a fine-tuned version of microsoft/speecht5_tts on the VoxPopuli hr dataset. It achieves the following results on the evaluation set:
- Loss: 0.4304
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: 8
- 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
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4915 | 3.24 | 1000 | 0.4504 |
| 0.4757 | 6.49 | 2000 | 0.4366 |
| 0.4653 | 9.73 | 3000 | 0.4318 |
| 0.4636 | 12.98 | 4000 | 0.4304 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
