metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_tts_voxpopuli_nl
results: []
speecht5_tts_voxpopuli_nl
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: 0.4839
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: 8
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8047 | 1.6667 | 100 | 0.6467 |
| 0.6735 | 3.3333 | 200 | 0.5503 |
| 0.6013 | 5.0 | 300 | 0.5084 |
| 0.5619 | 6.6667 | 400 | 0.4996 |
| 0.5466 | 8.3333 | 500 | 0.4909 |
| 0.5313 | 10.0 | 600 | 0.4864 |
| 0.5283 | 11.6667 | 700 | 0.4851 |
| 0.5372 | 13.3333 | 800 | 0.4846 |
| 0.5266 | 15.0 | 900 | 0.4855 |
| 0.5258 | 16.6667 | 1000 | 0.4839 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0