michaelsh/speecht5_finetuned_voxpopuli_it
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: 0.4934
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: 8000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5493 | 10.24 | 1000 | 0.5049 |
| 0.52 | 20.49 | 2000 | 0.4968 |
| 0.5082 | 30.73 | 3000 | 0.4883 |
| 0.5006 | 40.97 | 4000 | 0.4914 |
| 0.4954 | 51.22 | 5000 | 0.4910 |
| 0.4884 | 61.46 | 6000 | 0.4953 |
| 0.4845 | 71.7 | 7000 | 0.4939 |
| 0.4916 | 81.95 | 8000 | 0.4934 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3