speecht5_tts_srpski_v2.0
This model is a fine-tuned version of microsoft/speecht5_tts on the srpski_dataset_v4 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4424
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5492 | 1.4688 | 1000 | 0.4743 |
| 0.4917 | 2.9375 | 2000 | 0.4521 |
| 0.4709 | 4.4056 | 3000 | 0.4460 |
| 0.4754 | 5.8744 | 4000 | 0.4424 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 3
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for milans213/speecht5_tts_srpski_v2.0
Base model
microsoft/speecht5_tts