Downloads · 30 days
5
5% of all-time downloads
senga-LUK-20k-clean-speecht5
sil-ai/senga-LUK-20k-clean-speecht5
senga-LUK-20k-clean-speecht5 is a text-to-audio model from sil-ai. 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
94
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
- Jul 3, 2026
- Updated
- Jul 3, 2026
- SHA
- 1337fab9
Base models
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. -->
senga-LUK-20k-clean-speecht5
This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1049
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 3407
- gradient_accumulation_steps: 4
- 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: cosine
- lr_scheduler_warmup_steps: 2000
- training_steps: 20000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0933 | 90.9091 | 1000 | 0.0817 |
| 0.076 | 181.8182 | 2000 | 0.0809 |
| 0.0629 | 272.7273 | 3000 | 0.0836 |
| 0.0599 | 363.6364 | 4000 | 0.0844 |
| 0.0559 | 454.5455 | 5000 | 0.0894 |
| 0.0511 | 545.4545 | 6000 | 0.0913 |
| 0.0478 | 636.3636 | 7000 | 0.0950 |
| 0.0436 | 727.2727 | 8000 | 0.0971 |
| 0.045 | 818.1818 | 9000 | 0.0973 |
| 0.0407 | 909.0909 | 10000 | 0.1029 |
| 0.0395 | 1000.0 | 11000 | 0.1021 |
| 0.0409 | 1090.9091 | 12000 | 0.1015 |
| 0.0372 | 1181.8182 | 13000 | 0.1045 |
| 0.038 | 1272.7273 | 14000 | 0.1031 |
| 0.0356 | 1363.6364 | 15000 | 0.1075 |
| 0.0369 | 1454.5455 | 16000 | 0.1048 |
| 0.0362 | 1545.4545 | 17000 | 0.1046 |
| 0.0421 | 1636.3636 | 18000 | 0.1072 |
| 0.0364 | 1727.2727 | 19000 | 0.1068 |
| 0.0381 | 1818.1818 | 20000 | 0.1049 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu128
- Datasets 4.2.0
- Tokenizers 0.22.2
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026