speecht5_finetuned_librispeech_polish_epo15_batch4_gas4
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: 0.3677
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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use 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: 200
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7707 | 2.0409 | 200 | 0.4218 |
| 1.6529 | 4.0818 | 400 | 0.3891 |
| 1.6267 | 6.1228 | 600 | 0.3841 |
| 1.5803 | 8.1637 | 800 | 0.3760 |
| 1.5244 | 10.2046 | 1000 | 0.3709 |
| 1.5433 | 12.2455 | 1200 | 0.3707 |
| 1.5127 | 14.2864 | 1400 | 0.3677 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 15
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 Dawid511/speecht5_finetuned_librispeech_polish_epo15_batch4_gas4
Base model
microsoft/speecht5_tts