Downloads · 30 days
13
35% of all-time downloads
speecht5_sotuvchi_03
Akbarkhon/speecht5_sotuvchi_03
speecht5_sotuvchi_03 is a text-to-audio model from Akbarkhon. 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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
37
Public
Parameters
144M
13.9 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
- Model type
- speecht5
- Access
- Public
- Created
- Apr 3, 2025
- Updated
- Apr 3, 2025
- SHA
- 406cb1b8
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_sotuvchi_03
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6782
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: 2e-05
- train_batch_size: 128
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- optimizer: Use 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: 500
- num_epochs: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6191 | 50.0 | 50 | 1.0185 |
| 0.6084 | 100.0 | 100 | 0.9518 |
| 0.5364 | 150.0 | 150 | 0.8739 |
| 0.4962 | 200.0 | 200 | 0.8089 |
| 0.4986 | 250.0 | 250 | 0.7600 |
| 0.4271 | 300.0 | 300 | 0.7515 |
| 0.3937 | 350.0 | 350 | 0.7359 |
| 0.3983 | 400.0 | 400 | 0.7291 |
| 0.3982 | 450.0 | 450 | 0.7349 |
| 0.3734 | 500.0 | 500 | 0.7077 |
| 0.3786 | 550.0 | 550 | 0.7153 |
| 0.3852 | 600.0 | 600 | 0.7076 |
| 0.3563 | 650.0 | 650 | 0.6961 |
| 0.3341 | 700.0 | 700 | 0.6844 |
| 0.3373 | 750.0 | 750 | 0.6823 |
| 0.355 | 800.0 | 800 | 0.6804 |
| 0.3401 | 850.0 | 850 | 0.6811 |
| 0.3401 | 900.0 | 900 | 0.6824 |
| 0.3374 | 950.0 | 950 | 0.6792 |
| 0.3293 | 1000.0 | 1000 | 0.6782 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- Created
- Apr 3, 2025
- Updated
- Apr 3, 2025