metadata
library_name: transformers
license: mit
base_model: MBZUAI/speecht5_tts_clartts_ar
tags:
- generated_from_trainer
model-index:
- name: Sindhi-TTS
results: []
Sindhi-TTS
This model is a fine-tuned version of MBZUAI/speecht5_tts_clartts_ar on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5882
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- 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: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6706 | 0.1996 | 100 | 0.6716 |
| 0.6365 | 0.3992 | 200 | 0.6357 |
| 0.6266 | 0.5988 | 300 | 0.6185 |
| 0.6172 | 0.7984 | 400 | 0.6162 |
| 0.6011 | 0.9980 | 500 | 0.6083 |
| 0.6047 | 1.1976 | 600 | 0.6041 |
| 0.5943 | 1.3972 | 700 | 0.6023 |
| 0.597 | 1.5968 | 800 | 0.5936 |
| 0.5927 | 1.7964 | 900 | 0.5884 |
| 0.5932 | 1.9960 | 1000 | 0.5882 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3