Downloads · 30 days
7
15% of all-time downloads
mahinda_check1
kavinda123321/mahinda_check1
mahinda_check1 is a text-to-audio model from kavinda123321. 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
47
Public
Parameters
336M
3.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 98%
At a glance
- Task
- Text-to-Audio
- Library
- transformers
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- May 16, 2025
- Updated
- May 28, 2025
- SHA
- a654472b
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. -->
mahinda_check1
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: 0.5982
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: 4e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 10
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5426 | 1.0 | 42 | 0.6406 |
| 0.5337 | 2.0 | 84 | 0.6315 |
| 0.525 | 3.0 | 126 | 0.6253 |
| 0.5173 | 4.0 | 168 | 0.6234 |
| 0.5043 | 5.0 | 210 | 0.6203 |
| 0.5003 | 6.0 | 252 | 0.6247 |
| 0.4904 | 7.0 | 294 | 0.6182 |
| 0.4884 | 8.0 | 336 | 0.6152 |
| 0.4791 | 9.0 | 378 | 0.6164 |
| 0.4755 | 10.0 | 420 | 0.6107 |
| 0.4733 | 11.0 | 462 | 0.6122 |
| 0.4677 | 12.0 | 504 | 0.6062 |
| 0.4712 | 13.0 | 546 | 0.5999 |
| 0.4654 | 14.0 | 588 | 0.6035 |
| 0.4587 | 15.0 | 630 | 0.6017 |
| 0.4595 | 16.0 | 672 | 0.6025 |
| 0.4528 | 17.0 | 714 | 0.6077 |
| 0.4549 | 18.0 | 756 | 0.6019 |
| 0.4538 | 19.0 | 798 | 0.6014 |
| 0.4553 | 20.0 | 840 | 0.5982 |
Framework versions
- Transformers 4.52.2
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- May 16, 2025
- Updated
- May 28, 2025