Downloads · 30 days
7
6% of all-time downloads
speecht5_tts_fa_kh
K-Hooshanfar/speecht5_tts_fa_kh
speecht5_tts_fa_kh is a text-to-audio model from K-Hooshanfar. 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
108
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
- Jan 25, 2024
- Updated
- Jan 31, 2024
- SHA
- 65de877e
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_tts_fa_kh
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: 0.4608
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: 500
- training_steps: 7000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6355 | 0.61 | 500 | 0.6008 |
| 0.5802 | 1.22 | 1000 | 0.5700 |
| 0.5703 | 1.83 | 1500 | 0.5321 |
| 0.5534 | 2.44 | 2000 | 0.5320 |
| 0.5441 | 3.05 | 2500 | 0.5198 |
| 0.538 | 3.66 | 3000 | 0.5023 |
| 0.514 | 4.27 | 3500 | 0.4917 |
| 0.5191 | 4.88 | 4000 | 0.4896 |
| 0.5002 | 5.49 | 4500 | 0.4814 |
| 0.4894 | 6.1 | 5000 | 0.4746 |
| 0.4865 | 6.71 | 5500 | 0.4681 |
| 0.4844 | 7.32 | 6000 | 0.4639 |
| 0.4824 | 7.93 | 6500 | 0.4587 |
| 0.4771 | 8.54 | 7000 | 0.4608 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- Jan 25, 2024
- Updated
- Jan 31, 2024