Downloads · 30 days
11
29% of all-time downloads
speecht5_finetuned_voxpopuli_hu
sugafree/speecht5_finetuned_voxpopuli_hu
speecht5_finetuned_voxpopuli_hu is a text-to-audio model from sugafree. 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
38
Public
Parameters
144M
2.3 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
- Feb 17, 2024
- Updated
- Feb 17, 2024
- SHA
- 13d58504
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. -->
Facebook voxpopuli HU - Tamas Szilagyi
This model is a fine-tuned version of microsoft/speecht5_tts on the Facebook voxpopuli Hungarian dataset. It achieves the following results on the evaluation set:
- Loss: 0.4834
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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4969 | 42.33 | 1000 | 0.4739 |
| 0.4629 | 84.66 | 2000 | 0.4770 |
| 0.4527 | 126.98 | 3000 | 0.4806 |
| 0.4517 | 169.31 | 4000 | 0.4834 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.17.0
- Tokenizers 0.15.2
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Languages
- hu
- Created
- Feb 17, 2024
- Updated
- Feb 17, 2024