Downloads · 30 days
7
7% of all-time downloads
zlm_b64_le5_s12000
mikhail-panzo/zlm_b64_le5_s12000
zlm_b64_le5_s12000 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
98
Public
Parameters
144M
62.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt27.7 GB · 66%
At a glance
- Task
- Text-to-Audio
- Library
- transformers
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- Apr 29, 2024
- Updated
- Apr 30, 2024
- SHA
- c125facb
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. -->
zlm_b64_le5_s12000
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: 0.3623
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: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- training_steps: 12000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7129 | 0.4188 | 500 | 0.6066 |
| 0.5922 | 0.8375 | 1000 | 0.4980 |
| 0.5168 | 1.2563 | 1500 | 0.4579 |
| 0.4954 | 1.6750 | 2000 | 0.4383 |
| 0.4836 | 2.0938 | 2500 | 0.4208 |
| 0.4623 | 2.5126 | 3000 | 0.4098 |
| 0.4499 | 2.9313 | 3500 | 0.4003 |
| 0.4421 | 3.3501 | 4000 | 0.3942 |
| 0.4345 | 3.7688 | 4500 | 0.3894 |
| 0.4233 | 4.1876 | 5000 | 0.3840 |
| 0.4288 | 4.6064 | 5500 | 0.3808 |
| 0.4218 | 5.0251 | 6000 | 0.3775 |
| 0.4174 | 5.4439 | 6500 | 0.3746 |
| 0.4075 | 5.8626 | 7000 | 0.3744 |
| 0.4042 | 6.2814 | 7500 | 0.3715 |
| 0.4075 | 6.7002 | 8000 | 0.3695 |
| 0.4064 | 7.1189 | 8500 | 0.3666 |
| 0.4007 | 7.5377 | 9000 | 0.3663 |
| 0.399 | 7.9564 | 9500 | 0.3649 |
| 0.4152 | 8.3752 | 10000 | 0.3647 |
| 0.4033 | 8.7940 | 10500 | 0.3640 |
| 0.4011 | 9.2127 | 11000 | 0.3628 |
| 0.4002 | 9.6315 | 11500 | 0.3631 |
| 0.3975 | 10.0503 | 12000 | 0.3623 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- Apr 29, 2024
- Updated
- Apr 30, 2024