metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- tts
model-index:
- name: speecht5_tts
results: []
speecht5_tts
This model is a fine-tuned version of microsoft/speecht5_tts on the tts dataset. It achieves the following results on the evaluation set:
- Loss: 0.3536
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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 |
|---|---|---|---|
| 0.5334 | 1.8149 | 1000 | 0.4285 |
| 0.4373 | 3.6298 | 2000 | 0.3785 |
| 0.4276 | 5.4446 | 3000 | 0.3582 |
| 0.3996 | 7.2595 | 4000 | 0.3536 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0