metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- voxpopuli
model-index:
- name: checkpoint
results: []
checkpoint
This model is a fine-tuned version of microsoft/speecht5_tts on the voxpopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.4609
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 OptimizerNames.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: 900
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4918 | 0.7188 | 100 | 0.4853 |
| 0.4883 | 1.4313 | 200 | 0.4813 |
| 0.468 | 2.1438 | 300 | 0.4766 |
| 0.4826 | 2.8625 | 400 | 0.4665 |
| 0.4843 | 3.5750 | 500 | 0.4688 |
| 0.4743 | 4.2875 | 600 | 0.4632 |
| 0.4607 | 5.0 | 700 | 0.4627 |
| 0.4699 | 5.7188 | 800 | 0.4623 |
| 0.4668 | 6.4313 | 900 | 0.4609 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1