speecht5-finetuned-voxpopuli_sl
This model is a fine-tuned version of microsoft/speecht5_tts on the facebook/voxpopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.4830
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: 250
- training_steps: 2500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5689 | 2.68 | 250 | 0.5361 |
| 0.5153 | 5.35 | 500 | 0.5024 |
| 0.5044 | 8.03 | 750 | 0.4942 |
| 0.4934 | 10.71 | 1000 | 0.4915 |
| 0.4906 | 13.39 | 1250 | 0.4853 |
| 0.4886 | 16.06 | 1500 | 0.4868 |
| 0.4886 | 18.74 | 1750 | 0.4842 |
| 0.4812 | 21.42 | 2000 | 0.4849 |
| 0.4824 | 24.1 | 2250 | 0.4836 |
| 0.48 | 26.77 | 2500 | 0.4830 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3