Downloads · 30 days
4
13% of all-time downloads
speecht5_tts_dysarthria_v1
miosipof/speecht5_tts_dysarthria_v1
speecht5_tts_dysarthria_v1 is a machine learning model from miosipof. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
All-time downloads
30
Public
Parameters
144M
6.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors578 MB · 100%
At a glance
- Model type
- speecht5
- Access
- Public
- Created
- Oct 26, 2024
- Updated
- Oct 26, 2024
- SHA
- a1f9bed5
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_dysarthria_v1
This model was trained from scratch on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5207
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-06
- 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: 50
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5385 | 0.7042 | 25 | 0.5221 |
| 0.5296 | 1.4085 | 50 | 0.5202 |
| 0.5471 | 2.1127 | 75 | 0.5208 |
| 0.5408 | 2.8169 | 100 | 0.5204 |
| 0.5497 | 3.5211 | 125 | 0.5198 |
| 0.5193 | 4.2254 | 150 | 0.5219 |
| 0.5317 | 4.9296 | 175 | 0.5184 |
| 0.5409 | 5.6338 | 200 | 0.5207 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.19.1
- Type
- speecht5
- Created
- Oct 26, 2024
- Updated
- Oct 26, 2024