metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: result
results: []
result
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: 0.4306
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: 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.3611 | 1.6949 | 100 | 0.4645 |
| 3.9124 | 3.3898 | 200 | 0.4499 |
| 3.7546 | 5.0847 | 300 | 0.4453 |
| 3.6216 | 6.7797 | 400 | 0.4333 |
| 3.5083 | 8.4746 | 500 | 0.4299 |
| 3.5245 | 10.1695 | 600 | 0.4295 |
| 3.4645 | 11.8644 | 700 | 0.4191 |
| 3.3739 | 13.5593 | 800 | 0.4218 |
| 3.3132 | 15.2542 | 900 | 0.4316 |
| 3.3192 | 16.9492 | 1000 | 0.4306 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0