metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- arrow
model-index:
- name: speecht5_finetuned_pl_inteligentne_full
results: []
speecht5_finetuned_pl_inteligentne_full
This model is a fine-tuned version of microsoft/speecht5_tts on the arrow dataset. It achieves the following results on the evaluation set:
- Loss: 0.4373
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 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 |
|---|---|---|---|
| 0.5195 | 8.8342 | 1000 | 0.4857 |
| 0.478 | 17.6751 | 2000 | 0.4510 |
| 0.4748 | 26.5159 | 3000 | 0.4418 |
| 0.4685 | 35.3568 | 4000 | 0.4373 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3