metadata
library_name: transformers
license: mit
base_model: MBZUAI/speecht5_tts_clartts_ar
tags:
- generated_from_trainer
model-index:
- name: Arabictts
results: []
Arabictts
This model is a fine-tuned version of MBZUAI/speecht5_tts_clartts_ar on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5791
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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 700
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6455 | 6.9565 | 100 | 0.6248 |
| 0.6067 | 13.9130 | 200 | 0.5949 |
| 0.5847 | 20.8696 | 300 | 0.5851 |
| 0.5713 | 27.8261 | 400 | 0.5806 |
| 0.5597 | 34.7826 | 500 | 0.5779 |
| 0.5525 | 41.7391 | 600 | 0.5832 |
| 0.5511 | 48.6957 | 700 | 0.5791 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3