--- library_name: transformers license: mit base_model: microsoft/speecht5_tts tags: - generated_from_trainer model-index: - name: speecht5_finetuned_kavinda results: [] --- # speecht5_finetuned_kavinda 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: 0.4658 ## 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: 500 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-------:|:----:|:---------------:| | 4.3658 | 8.3137 | 100 | 0.4656 | | 3.887 | 16.6275 | 200 | 0.4546 | | 3.6315 | 24.9412 | 300 | 0.4502 | | 3.5027 | 33.3137 | 400 | 0.4576 | | 3.3957 | 41.6275 | 500 | 0.4658 | ### Framework versions - Transformers 4.47.1 - Pytorch 2.5.1+cu121 - Datasets 3.2.0 - Tokenizers 0.21.0