| --- |
| library_name: transformers |
| license: mit |
| base_model: microsoft/speecht5_tts |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: maanta |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # maanta |
|
|
| This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0937 |
|
|
| ## 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 OptimizerNames.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: 500 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:------:|:----:|:---------------:| |
| | 0.3036 | 0.7111 | 100 | 0.2281 | |
| | 0.2044 | 1.4196 | 200 | 0.1568 | |
| | 0.1686 | 2.128 | 300 | 0.1183 | |
| | 0.1506 | 2.8391 | 400 | 0.0995 | |
| | 0.1439 | 3.5476 | 500 | 0.0937 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.52.4 |
| - Pytorch 2.6.0+cu124 |
| - Datasets 3.6.0 |
| - Tokenizers 0.21.1 |
|
|
