Downloads · 30 days
9
10% of all-time downloads
speecht5_finetuned_as-krn_tr
as-krn/speecht5_finetuned_as-krn_tr
speecht5_finetuned_as-krn_tr is a text-to-audio model from as-krn. 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
89
Public
Parameters
144M
2.9 GB on disk
Likes
1
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
- Aug 11, 2025
- Updated
- Aug 11, 2025
- SHA
- c34b2962
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. -->
speecht5_finetuned_as-krn_tr
This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3208
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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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: 100
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9613 | 0.1136 | 25 | 0.6422 |
| 0.6754 | 0.2273 | 50 | 0.5055 |
| 0.5625 | 0.3409 | 75 | 0.4486 |
| 0.4968 | 0.4545 | 100 | 0.4258 |
| 0.4747 | 0.5682 | 125 | 0.4223 |
| 0.4444 | 0.6818 | 150 | 0.3834 |
| 0.4196 | 0.7955 | 175 | 0.3776 |
| 0.4111 | 0.9091 | 200 | 0.3739 |
| 0.4004 | 1.0227 | 225 | 0.3519 |
| 0.3948 | 1.1364 | 250 | 0.3484 |
| 0.3783 | 1.25 | 275 | 0.3461 |
| 0.3798 | 1.3636 | 300 | 0.3357 |
| 0.3672 | 1.4773 | 325 | 0.3435 |
| 0.3628 | 1.5909 | 350 | 0.3344 |
| 0.3722 | 1.7045 | 375 | 0.3313 |
| 0.3542 | 1.8182 | 400 | 0.3294 |
| 0.3596 | 1.9318 | 425 | 0.3233 |
| 0.3475 | 2.0455 | 450 | 0.3238 |
| 0.3534 | 2.1591 | 475 | 0.3217 |
| 0.3419 | 2.2727 | 500 | 0.3208 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- Aug 11, 2025
- Updated
- Aug 11, 2025