metadata
library_name: transformers
license: mit
base_model: fahadqazi/Sindhi-TTS
tags:
- generated_from_trainer
model-index:
- name: Sindhi-TTS
results: []
Sindhi-TTS
This model is a fine-tuned version of fahadqazi/Sindhi-TTS on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4864
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- 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 |
|---|---|---|---|
| 0.6189 | 0.2298 | 100 | 0.5837 |
| 0.5426 | 0.4595 | 200 | 0.5275 |
| 0.5237 | 0.6893 | 300 | 0.5106 |
| 0.5118 | 0.9190 | 400 | 0.5018 |
| 0.5032 | 1.1488 | 500 | 0.4960 |
| 0.5044 | 1.3785 | 600 | 0.4939 |
| 0.5042 | 1.6083 | 700 | 0.4905 |
| 0.4985 | 1.8380 | 800 | 0.4895 |
| 0.4938 | 2.0678 | 900 | 0.4871 |
| 0.496 | 2.2975 | 1000 | 0.4864 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3