metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- audiofolder
model-index:
- name: speecht5_finetuned_voxpopuli_nl
results: []
speecht5_finetuned_voxpopuli_nl
This model is a fine-tuned version of microsoft/speecht5_tts on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7123
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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3587 | 5.71 | 10 | 0.8407 |
| 0.3256 | 11.43 | 20 | 0.7593 |
| 0.3727 | 17.14 | 30 | 0.7535 |
| 0.3344 | 22.86 | 40 | 0.7342 |
| 0.3175 | 28.57 | 50 | 0.7242 |
| 0.3036 | 34.29 | 60 | 0.7320 |
| 0.2998 | 40.0 | 70 | 0.7248 |
| 0.2901 | 45.71 | 80 | 0.6993 |
| 0.317 | 51.43 | 90 | 0.7162 |
| 0.3195 | 57.14 | 100 | 0.7123 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0