uz_2301_3.02_tts
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: 0.4160
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use 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: 500
- training_steps: 3000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5385 | 10.0 | 500 | 0.4527 |
| 0.4317 | 20.0 | 1000 | 0.4372 |
| 0.3981 | 30.0 | 1500 | 0.4087 |
| 0.3675 | 40.0 | 2000 | 0.4102 |
| 0.3485 | 50.0 | 2500 | 0.4075 |
| 0.3406 | 60.0 | 3000 | 0.4160 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 63
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Beehzod/uz_2301_3.02_tts
Base model
microsoft/speecht5_tts