T5 TTS finetuned on accented english - b-koopman
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: 0.4800
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: 500
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.632 | 1.05 | 100 | 0.5855 |
| 0.6262 | 2.11 | 200 | 0.5622 |
| 0.5991 | 3.16 | 300 | 0.5442 |
| 0.562 | 4.22 | 400 | 0.5110 |
| 0.5345 | 5.27 | 500 | 0.4929 |
| 0.5204 | 6.32 | 600 | 0.4888 |
| 0.5249 | 7.38 | 700 | 0.4835 |
| 0.5189 | 8.43 | 800 | 0.4812 |
| 0.5116 | 9.49 | 900 | 0.4798 |
| 0.5157 | 10.54 | 1000 | 0.4804 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3