Downloads · 30 days
1
3% of all-time downloads
speecht5_finetuned_english_ranil
kavinda123321/speecht5_finetuned_english_ranil
speecht5_finetuned_english_ranil 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
35
Public
Parameters
144M
578 MB 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
- May 2, 2025
- Updated
- May 2, 2025
- SHA
- 39ca4b70
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_english_ranil
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: 0.5627
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: 3e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- 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: 50
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7252 | 1.0 | 7 | 0.6931 |
| 0.6444 | 2.0 | 14 | 0.6860 |
| 0.5948 | 3.0 | 21 | 0.6016 |
| 0.5453 | 4.0 | 28 | 0.5579 |
| 0.4945 | 5.0 | 35 | 0.5652 |
| 0.4792 | 6.0 | 42 | 0.5520 |
| 0.4424 | 7.0 | 49 | 0.5520 |
| 0.4285 | 8.0 | 56 | 0.5383 |
| 0.4263 | 9.0 | 63 | 0.5343 |
| 0.4223 | 10.0 | 70 | 0.5590 |
| 0.4107 | 11.0 | 77 | 0.5349 |
| 0.3957 | 12.0 | 84 | 0.5345 |
| 0.3983 | 13.0 | 91 | 0.5336 |
| 0.3981 | 14.0 | 98 | 0.5350 |
| 0.3954 | 15.0 | 105 | 0.5460 |
| 0.3836 | 16.0 | 112 | 0.5375 |
| 0.3791 | 17.0 | 119 | 0.5391 |
| 0.3874 | 18.0 | 126 | 0.5368 |
| 0.3728 | 19.0 | 133 | 0.5466 |
| 0.3695 | 20.0 | 140 | 0.5483 |
| 0.3678 | 21.0 | 147 | 0.5500 |
| 0.3664 | 22.0 | 154 | 0.5465 |
| 0.3766 | 23.0 | 161 | 0.5416 |
| 0.3762 | 24.0 | 168 | 0.5479 |
| 0.3854 | 25.0 | 175 | 0.5541 |
| 0.3655 | 26.0 | 182 | 0.5458 |
| 0.3652 | 27.0 | 189 | 0.5535 |
| 0.365 | 28.0 | 196 | 0.5521 |
| 0.3629 | 29.0 | 203 | 0.5479 |
| 0.3618 | 30.0 | 210 | 0.5587 |
| 0.3637 | 31.0 | 217 | 0.5665 |
| 0.3629 | 32.0 | 224 | 0.5560 |
| 0.3523 | 33.0 | 231 | 0.5606 |
| 0.354 | 34.0 | 238 | 0.5583 |
| 0.3582 | 35.0 | 245 | 0.5583 |
| 0.3507 | 36.0 | 252 | 0.5561 |
| 0.356 | 37.0 | 259 | 0.5651 |
| 0.3533 | 38.0 | 266 | 0.5664 |
| 0.352 | 39.0 | 273 | 0.5620 |
| 0.3489 | 40.0 | 280 | 0.5657 |
| 0.3569 | 41.0 | 287 | 0.5698 |
| 0.3466 | 42.0 | 294 | 0.5623 |
| 0.3697 | 42.9057 | 300 | 0.5627 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- May 2, 2025
- Updated
- May 2, 2025