Downloads · 30 days
5
7% of all-time downloads
speecht5_finetuned_voxpopuli_sl
bogosla/speecht5_finetuned_voxpopuli_sl
speecht5_finetuned_voxpopuli_sl is a text-to-audio model from bogosla. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
71
Public
Parameters
144M
4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors578 MB · 100%
At a glance
- Task
- Text-to-Audio
- Library
- transformers
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- Jan 8, 2026
- Updated
- Jan 8, 2026
- SHA
- eb7eb686
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
speecht5_tts Slovene
This model is a fine-tuned version of microsoft/speecht5_tts on the voxpopul Slovene dataset. It achieves the following results on the evaluation set:
- Loss: 0.5796
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: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 500
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7475 | 1.0 | 30 | 0.6915 |
| 0.7437 | 2.0 | 60 | 0.6568 |
| 0.7125 | 3.0 | 90 | 0.6337 |
| 0.6797 | 4.0 | 120 | 0.6143 |
| 0.6492 | 5.0 | 150 | 0.6021 |
| 0.6272 | 6.0 | 180 | 0.5898 |
| 0.618 | 7.0 | 210 | 0.5800 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.8.0+cu129
- Datasets 3.6.0
- Tokenizers 0.22.1
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Languages
- sl
- Created
- Jan 8, 2026
- Updated
- Jan 8, 2026