--- library_name: transformers license: mit base_model: microsoft/speecht5_tts tags: - generated_from_trainer model-index: - name: speecht5_tts_uz results: [] --- # speecht5_tts_uz 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: 0.4040 ## 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: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - 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 | |:-------------:|:-------:|:----:|:---------------:| | 0.528 | 4.7619 | 100 | 0.4651 | | 0.4746 | 9.5238 | 200 | 0.4241 | | 0.4649 | 14.2857 | 300 | 0.4114 | | 0.4509 | 19.0476 | 400 | 0.4059 | | 0.4612 | 23.8095 | 500 | 0.4040 | ### Framework versions - Transformers 4.49.0.dev0 - Pytorch 2.5.1+cu121 - Datasets 3.2.0 - Tokenizers 0.21.0