SpeechT5 TTS Tunisien
This model is a fine-tuned version of MBZUAI/speecht5_tts_clartts_ar on the Tunisian_dataset_STT-TTS15s_filtred1.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4883
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-05
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5165 | 34.48 | 1000 | 0.4983 |
| 0.505 | 68.97 | 2000 | 0.4893 |
| 0.4996 | 103.45 | 3000 | 0.4876 |
| 0.4968 | 137.93 | 4000 | 0.4883 |
Framework versions
- Transformers 4.35.1
- Pytorch 2.3.1+cu121
- Datasets 2.14.7
- Tokenizers 0.14.1
- Downloads last month
- 1