Downloads · 30 days
3
2% of all-time downloads
senga-LUK-aligned-stoploss-speecht5
sil-ai/senga-LUK-aligned-stoploss-speecht5
senga-LUK-aligned-stoploss-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
147
Public
Parameters
144M
4.6 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 2, 2026
- Updated
- Jul 3, 2026
- SHA
- c76eac64
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-aligned-stoploss-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: 0.1300
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: 4000
- training_steps: 40000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1049 | 90.9091 | 1000 | 0.0889 |
| 0.0821 | 181.8182 | 2000 | 0.0786 |
| 0.071 | 272.7273 | 3000 | 0.0832 |
| 0.0661 | 363.6364 | 4000 | 0.0827 |
| 0.0585 | 454.5455 | 5000 | 0.0884 |
| 0.0573 | 545.4545 | 6000 | 0.0928 |
| 0.0527 | 636.3636 | 7000 | 0.0945 |
| 0.0463 | 727.2727 | 8000 | 0.0995 |
| 0.0472 | 818.1818 | 9000 | 0.1012 |
| 0.0434 | 909.0909 | 10000 | 0.1027 |
| 0.041 | 1000.0 | 11000 | 0.1036 |
| 0.0424 | 1090.9091 | 12000 | 0.1060 |
| 0.0389 | 1181.8182 | 13000 | 0.1095 |
| 0.0389 | 1272.7273 | 14000 | 0.1109 |
| 0.0366 | 1363.6364 | 15000 | 0.1121 |
| 0.037 | 1454.5455 | 16000 | 0.1157 |
| 0.0357 | 1545.4545 | 17000 | 0.1140 |
| 0.0467 | 1636.3636 | 18000 | 0.1234 |
| 0.0343 | 1727.2727 | 19000 | 0.1210 |
| 0.0358 | 1818.1818 | 20000 | 0.1192 |
| 0.0313 | 1909.0909 | 21000 | 0.1212 |
| 0.0328 | 2000.0 | 22000 | 0.1213 |
| 0.0317 | 2090.9091 | 23000 | 0.1212 |
| 0.0319 | 2181.8182 | 24000 | 0.1236 |
| 0.0311 | 2272.7273 | 25000 | 0.1252 |
| 0.0306 | 2363.6364 | 26000 | 0.1237 |
| 0.0289 | 2454.5455 | 27000 | 0.1270 |
| 0.028 | 2545.4545 | 28000 | 0.1270 |
| 0.0295 | 2636.3636 | 29000 | 0.1262 |
| 0.0302 | 2727.2727 | 30000 | 0.1272 |
| 0.0375 | 2818.1818 | 31000 | 0.1275 |
| 0.028 | 2909.0909 | 32000 | 0.1289 |
| 0.0272 | 3000.0 | 33000 | 0.1265 |
| 0.0292 | 3090.9091 | 34000 | 0.1280 |
| 0.0269 | 3181.8182 | 35000 | 0.1278 |
| 0.0264 | 3272.7273 | 36000 | 0.1289 |
| 0.0285 | 3363.6364 | 37000 | 0.1300 |
| 0.0275 | 3454.5455 | 38000 | 0.1287 |
| 0.0285 | 3545.4545 | 39000 | 0.1293 |
| 0.0282 | 3636.3636 | 40000 | 0.1300 |
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 2, 2026
- Updated
- Jul 3, 2026