Downloads · 30 days
0
speecht5_tts_en_emotion
woodwardmw/speecht5_tts_en_emotion
speecht5_tts_en_emotion is a machine learning model from woodwardmw. Use it for the machine learning 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. --
Access
Public
Updated Nov 21, 2025
Parameters
144M
2.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors578 MB · 100%
At a glance
- Library
- transformers
- License
- mit
- Access
- Public
- Created
- Nov 21, 2025
- Updated
- Nov 21, 2025
- SHA
- 79705e97
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_en_emotion
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: 0.0527
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: 24
- eval_batch_size: 24
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4114 | 5.32 | 500 | 0.0788 |
| 0.3822 | 10.64 | 1000 | 0.0693 |
| 0.3408 | 15.96 | 1500 | 0.0687 |
| 0.3143 | 21.2773 | 2000 | 0.0647 |
| 0.3192 | 26.5973 | 2500 | 0.0644 |
| 0.3198 | 31.9173 | 3000 | 0.0601 |
| 0.3057 | 37.2347 | 3500 | 0.0600 |
| 0.2992 | 42.5547 | 4000 | 0.0605 |
| 0.305 | 47.8747 | 4500 | 0.0598 |
| 0.2823 | 53.192 | 5000 | 0.0566 |
| 0.2524 | 58.512 | 5500 | 0.0567 |
| 0.2573 | 63.832 | 6000 | 0.0563 |
| 0.2582 | 69.1493 | 6500 | 0.0556 |
| 0.2591 | 74.4693 | 7000 | 0.0558 |
| 0.2508 | 79.7893 | 7500 | 0.0540 |
| 0.2494 | 85.1067 | 8000 | 0.0531 |
| 0.2404 | 90.4267 | 8500 | 0.0536 |
| 0.2235 | 95.7467 | 9000 | 0.0532 |
| 0.235 | 101.064 | 9500 | 0.0531 |
| 0.2421 | 106.384 | 10000 | 0.0527 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu128
- Datasets 4.2.0
- Tokenizers 0.22.1
- Library
- transformers
- License
- mit
- Created
- Nov 21, 2025
- Updated
- Nov 21, 2025