metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
- text-to-speech
datasets:
- facebook/voxpopuli
model-index:
- name: speecht5_finetuned_voxpopuli_hr
results: []
speecht5_finetuned_voxpopuli_hr
This model is a fine-tuned version of microsoft/speecht5_tts on the facebook/voxpopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.5769
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: 1
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- 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: 5
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7244 | 0.0119 | 10 | 0.6521 |
| 0.6997 | 0.0239 | 20 | 0.6255 |
| 0.5865 | 0.0358 | 30 | 0.6029 |
| 0.593 | 0.0478 | 40 | 0.5946 |
| 0.6074 | 0.0597 | 50 | 0.5896 |
| 0.5793 | 0.0717 | 60 | 0.5830 |
| 0.5679 | 0.0836 | 70 | 0.5806 |
| 0.5869 | 0.0955 | 80 | 0.5793 |
| 0.5647 | 0.1075 | 90 | 0.5777 |
| 0.5902 | 0.1194 | 100 | 0.5769 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0