speecht5_finetuned_voxpopuli_ro
This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4394
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: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3127 | 3.0305 | 100 | 0.5046 |
| 2.0210 | 6.0611 | 200 | 0.4666 |
| 1.9349 | 9.0916 | 300 | 0.4549 |
| 1.8678 | 12.1221 | 400 | 0.4557 |
| 1.8350 | 15.1527 | 500 | 0.4458 |
| 1.7924 | 18.1832 | 600 | 0.4420 |
| 1.7497 | 21.2137 | 700 | 0.4426 |
| 1.7502 | 24.2443 | 800 | 0.4408 |
| 1.7198 | 27.2748 | 900 | 0.4381 |
| 1.7092 | 30.3053 | 1000 | 0.4394 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2