speecht5_finetuned_emirhan_tr
This model is a fine-tuned version of microsoft/speecht5_tts on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5641
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: 0.0001
- 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7879 | 0.3972 | 100 | 0.6982 |
| 0.7078 | 0.7944 | 200 | 0.6603 |
| 0.6728 | 1.1917 | 300 | 0.6420 |
| 0.646 | 1.5889 | 400 | 0.5979 |
| 0.6276 | 1.9861 | 500 | 0.5954 |
| 0.6213 | 2.3833 | 600 | 0.5852 |
| 0.6161 | 2.7805 | 700 | 0.5805 |
| 0.6043 | 3.1778 | 800 | 0.5701 |
| 0.6012 | 3.5750 | 900 | 0.5624 |
| 0.5951 | 3.9722 | 1000 | 0.5641 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.3.0+cu118
- Datasets 3.0.0
- Tokenizers 0.19.1