metadata
language:
- sl
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
- text-to-speech
datasets:
- facebook/voxpopuli
model-index:
- name: speecht5-finetuned-voxpopuli-sl
results: []
speecht5-finetuned-voxpopuli-sl
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: 0.4598
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: 16
- seed: 42
- gradient_accumulation_steps: 2
- 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: 125
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6473 | 3.39 | 100 | 0.5703 |
| 0.5709 | 6.78 | 200 | 0.4998 |
| 0.5339 | 10.17 | 300 | 0.4802 |
| 0.5158 | 13.56 | 400 | 0.4733 |
| 0.5275 | 16.95 | 500 | 0.4691 |
| 0.4983 | 20.34 | 600 | 0.4671 |
| 0.499 | 23.73 | 700 | 0.4638 |
| 0.5003 | 27.12 | 800 | 0.4610 |
| 0.496 | 30.51 | 900 | 0.4610 |
| 0.4935 | 33.9 | 1000 | 0.4598 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3