--- license: mit base_model: microsoft/speecht5_tts tags: - generated_from_trainer - audio - text-to-speech datasets: - fleurs model-index: - name: speecht5_finetuned_fleurs_zh results: [] --- # speecht5_finetuned_fleurs_zh This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co./microsoft/speecht5_tts) on the fleurs dataset. It achieves the following results on the evaluation set: - Loss: 0.4343 ## 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: 4 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 400 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.6864 | 1.09 | 100 | 0.6009 | | 0.5976 | 2.19 | 200 | 0.5062 | | 0.543 | 3.28 | 300 | 0.4577 | | 0.4786 | 4.38 | 400 | 0.4343 | ### Framework versions - Transformers 4.32.1 - Pytorch 2.0.1+cu118 - Datasets 2.14.4 - Tokenizers 0.13.3