metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_emirhan_tr
results: []
speecht5_finetuned_emirhan_tr
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: 0.4265
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 |
|---|---|---|---|
| 0.5818 | 1.0374 | 100 | 0.5152 |
| 0.5144 | 2.0748 | 200 | 0.4656 |
| 0.4944 | 3.1123 | 300 | 0.4559 |
| 0.481 | 4.1497 | 400 | 0.4455 |
| 0.4747 | 5.1871 | 500 | 0.4373 |
| 0.4594 | 6.2245 | 600 | 0.4329 |
| 0.4562 | 7.2619 | 700 | 0.4323 |
| 0.4521 | 8.2994 | 800 | 0.4278 |
| 0.447 | 9.3368 | 900 | 0.4261 |
| 0.4439 | 10.3742 | 1000 | 0.4265 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3