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: 0.5655
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 |
|---|---|---|---|
| 0.6259 | 8.1509 | 50 | 0.6030 |
| 0.5631 | 16.3019 | 100 | 0.5849 |
| 0.5468 | 24.4528 | 150 | 0.5856 |
| 0.5217 | 32.6038 | 200 | 0.5570 |
| 0.5102 | 40.7547 | 250 | 0.5555 |
| 0.4944 | 48.9057 | 300 | 0.5534 |
| 0.4829 | 57.1321 | 350 | 0.5509 |
| 0.477 | 65.2830 | 400 | 0.5567 |
| 0.4692 | 73.4340 | 450 | 0.5552 |
| 0.4635 | 81.5849 | 500 | 0.5572 |
| 0.4592 | 89.7358 | 550 | 0.5573 |
| 0.4546 | 97.8868 | 600 | 0.5610 |
| 0.4515 | 106.1132 | 650 | 0.5653 |
| 0.45 | 114.2642 | 700 | 0.5655 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3