| language: | |
| - en | |
| license: mit | |
| tags: | |
| - text-to-speech | |
| - generated_from_trainer | |
| datasets: | |
| - mozilla/commonvoice | |
| base_model: microsoft/speecht5_tts | |
| model-index: | |
| - name: SpeechT5 TTS English | |
| 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. --> | |
| # SpeechT5 TTS English | |
| This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the commonvoice dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.4261 | |
| ## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - lr_scheduler_warmup_steps: 500 | |
| - training_steps: 4000 | |
| - mixed_precision_training: Native AMP | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | | |
| |:-------------:|:-----:|:----:|:---------------:| | |
| | 0.4543 | 13.61 | 1000 | 0.4225 | | |
| | 0.4525 | 27.21 | 2000 | 0.4203 | | |
| | 0.4359 | 40.82 | 3000 | 0.4228 | | |
| | 0.4324 | 54.42 | 4000 | 0.4261 | | |
| ### Framework versions | |
| - Transformers 4.30.0.dev0 | |
| - Pytorch 2.0.1+cu118 | |
| - Datasets 2.12.0 | |
| - Tokenizers 0.13.3 | |