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: 0.5481
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: 900
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6582 | 3.7736 | 50 | 0.5892 |
| 0.603 | 7.5472 | 100 | 0.5603 |
| 0.5828 | 11.3208 | 150 | 0.5545 |
| 0.566 | 15.0943 | 200 | 0.5418 |
| 0.5504 | 18.8679 | 250 | 0.5393 |
| 0.5379 | 22.6415 | 300 | 0.5357 |
| 0.534 | 26.4151 | 350 | 0.5347 |
| 0.5226 | 30.1887 | 400 | 0.5352 |
| 0.5159 | 33.9623 | 450 | 0.5335 |
| 0.5058 | 37.7358 | 500 | 0.5350 |
| 0.5048 | 41.5094 | 550 | 0.5356 |
| 0.4994 | 45.2830 | 600 | 0.5367 |
| 0.4939 | 49.0566 | 650 | 0.5370 |
| 0.4923 | 52.8302 | 700 | 0.5366 |
| 0.488 | 56.6038 | 750 | 0.5397 |
| 0.4841 | 60.3774 | 800 | 0.5401 |
| 0.4834 | 64.1509 | 850 | 0.5490 |
| 0.4794 | 67.9245 | 900 | 0.5481 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3