uz-speecht5-own-voice
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: 0.6530
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: 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: 50
- training_steps: 800
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.6507 | 33.3810 | 100 | 0.7001 |
| 4.6170 | 66.7619 | 200 | 0.6547 |
| 4.1807 | 100.0 | 300 | 0.6334 |
| 4.1335 | 133.3810 | 400 | 0.6524 |
| 4.1555 | 166.7619 | 500 | 0.6574 |
| 4.0374 | 200.0 | 600 | 0.6506 |
| 4.0467 | 233.3810 | 700 | 0.6602 |
| 3.9265 | 266.7619 | 800 | 0.6530 |
Framework versions
- Transformers 5.15.0.dev0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2