Downloads · 30 days
6
30% of all-time downloads
malay_checkpoint
mikhail-panzo/malay_checkpoint
malay_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
20
Public
Parameters
144M
4.6 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 9, 2024
- Updated
- Apr 10, 2024
- SHA
- a1e3546e
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_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: 0.3983
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 2
- 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: 500
- training_steps: 8000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6478 | 0.21 | 500 | 0.5501 |
| 0.5541 | 0.42 | 1000 | 0.4814 |
| 0.5146 | 0.63 | 1500 | 0.4553 |
| 0.4821 | 0.84 | 2000 | 0.4413 |
| 0.4819 | 1.05 | 2500 | 0.4312 |
| 0.4574 | 1.26 | 3000 | 0.4236 |
| 0.4579 | 1.47 | 3500 | 0.4187 |
| 0.443 | 1.68 | 4000 | 0.4156 |
| 0.4525 | 1.88 | 4500 | 0.4095 |
| 0.4736 | 2.09 | 5000 | 0.4054 |
| 0.4486 | 2.3 | 5500 | 0.4045 |
| 0.4471 | 2.51 | 6000 | 0.4017 |
| 0.4436 | 2.72 | 6500 | 0.4012 |
| 0.456 | 2.93 | 7000 | 0.4000 |
| 0.432 | 3.14 | 7500 | 0.3991 |
| 0.4239 | 3.35 | 8000 | 0.3983 |
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 9, 2024
- Updated
- Apr 10, 2024