Downloads · 30 days
9
2% of all-time downloads
speecht5tts
Ocelotr/speecht5tts
speecht5tts is a text-to-audio model from Ocelotr. 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
470
Public
Repo size
2.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin578 MB · 100%
At a glance
- Task
- Text-to-Audio
- Library
- transformers
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- Jul 8, 2023
- Updated
- Jul 8, 2023
- SHA
- 6095c962
Datasets
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
This model is a fine-tuned version of microsoft/speecht5_tts on the SDA dataset. It achieves the following results on the evaluation set:
- Loss: 0.5062
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: 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: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5789 | 1.49 | 1000 | 0.5299 |
| 0.5448 | 2.97 | 2000 | 0.5150 |
| 0.5422 | 4.46 | 3000 | 0.5090 |
| 0.5417 | 5.95 | 4000 | 0.5062 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Languages
- ar
- Created
- Jul 8, 2023
- Updated
- Jul 8, 2023