Downloads · 30 days
12
17% of all-time downloads
malay_full_checkpoint
mikhail-panzo/malay_full_checkpoint
malay_full_checkpoint is a text-to-audio model from mikhail-panzo. 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
69
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
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- Apr 10, 2024
- Updated
- Apr 11, 2024
- SHA
- d9aaae19
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. -->
malay_full_checkpoint
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: 0.3226
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5538 | 0.21 | 500 | 0.4798 |
| 0.4888 | 0.42 | 1000 | 0.4282 |
| 0.4506 | 0.63 | 1500 | 0.4016 |
| 0.4269 | 0.84 | 2000 | 0.3948 |
| 0.4244 | 1.05 | 2500 | 0.3797 |
| 0.4009 | 1.26 | 3000 | 0.3672 |
| 0.3976 | 1.47 | 3500 | 0.3653 |
| 0.3903 | 1.68 | 4000 | 0.3560 |
| 0.38 | 1.88 | 4500 | 0.3525 |
| 0.3929 | 2.09 | 5000 | 0.3472 |
| 0.3799 | 2.3 | 5500 | 0.3459 |
| 0.3742 | 2.51 | 6000 | 0.3370 |
| 0.3713 | 2.72 | 6500 | 0.3364 |
| 0.3704 | 2.93 | 7000 | 0.3313 |
| 0.3569 | 3.14 | 7500 | 0.3307 |
| 0.3508 | 3.35 | 8000 | 0.3293 |
| 0.3544 | 3.56 | 8500 | 0.3288 |
| 0.3619 | 3.77 | 9000 | 0.3265 |
| 0.3542 | 3.98 | 9500 | 0.3239 |
| 0.361 | 4.19 | 10000 | 0.3226 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- Apr 10, 2024
- Updated
- Apr 11, 2024