Downloads · 30 days
2
1% of all-time downloads
speecht5_chathura_new1
kavinda123321/speecht5_chathura_new1
speecht5_chathura_new1 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
199
Public
Parameters
144M
13.3 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 18, 2025
- Updated
- Jul 18, 2025
- SHA
- 1a6e5f17
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_chathura_new1
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: 0.3372
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
- num_epochs: 25
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7029 | 1.0 | 39 | 0.5486 |
| 0.5438 | 2.0 | 78 | 0.4587 |
| 0.4734 | 3.0 | 117 | 0.4680 |
| 0.4537 | 4.0 | 156 | 0.4102 |
| 0.4321 | 5.0 | 195 | 0.3948 |
| 0.4207 | 6.0 | 234 | 0.3983 |
| 0.411 | 7.0 | 273 | 0.3908 |
| 0.4022 | 8.0 | 312 | 0.3823 |
| 0.3941 | 9.0 | 351 | 0.3750 |
| 0.3915 | 10.0 | 390 | 0.3689 |
| 0.3863 | 11.0 | 429 | 0.3659 |
| 0.38 | 12.0 | 468 | 0.3827 |
| 0.3759 | 13.0 | 507 | 0.3607 |
| 0.3711 | 14.0 | 546 | 0.3560 |
| 0.3669 | 15.0 | 585 | 0.3510 |
| 0.3618 | 16.0 | 624 | 0.3493 |
| 0.3617 | 17.0 | 663 | 0.3513 |
| 0.3592 | 18.0 | 702 | 0.3469 |
| 0.3542 | 19.0 | 741 | 0.3429 |
| 0.3534 | 20.0 | 780 | 0.3374 |
| 0.3525 | 21.0 | 819 | 0.3381 |
| 0.35 | 22.0 | 858 | 0.3359 |
| 0.3488 | 23.0 | 897 | 0.3362 |
| 0.3482 | 24.0 | 936 | 0.3357 |
| 0.3452 | 25.0 | 975 | 0.3372 |
Framework versions
- Transformers 4.53.2
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.2
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- Jul 18, 2025
- Updated
- Jul 18, 2025