metadata
library_name: transformers
language:
- nl
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- maguette
model-index:
- name: SpeechT5 TTS MT V0
results: []
SpeechT5 TTS MT V0
This model is a fine-tuned version of microsoft/speecht5_tts on the maguette dataset. It achieves the following results on the evaluation set:
- Loss: 1.2207
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 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: 10
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 6.6667 | 10 | 1.9046 |
| No log | 13.3333 | 20 | 1.5552 |
| 1.9023 | 20.0 | 30 | 1.4780 |
| 1.9023 | 26.6667 | 40 | 1.4256 |
| 1.567 | 33.3333 | 50 | 1.4126 |
| 1.567 | 40.0 | 60 | 1.3005 |
| 1.567 | 46.6667 | 70 | 1.2734 |
| 1.4002 | 53.3333 | 80 | 1.2259 |
| 1.4002 | 60.0 | 90 | 1.1843 |
| 1.2804 | 66.6667 | 100 | 1.2207 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3