| language: | |
| - en | |
| license: mit | |
| tags: | |
| - text-to-speech | |
| - generated_from_trainer | |
| datasets: | |
| - lj_speech | |
| base_model: Avitas8485/speecht5_tts_commonvoice_en_03 | |
| model-index: | |
| - name: speecht5_tts_commonvoice_en_04 | |
| 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_commonvoice_en_04 | |
| This model is a fine-tuned version of [Avitas8485/speecht5_tts_commonvoice_en_03](https://huggingface.co/Avitas8485/speecht5_tts_commonvoice_en_03) on the ljspeech dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.3719 | |
| ## 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: 8 | |
| - eval_batch_size: 8 | |
| - seed: 42 | |
| - gradient_accumulation_steps: 2 | |
| - total_train_batch_size: 16 | |
| - 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 | | |
| |:-------------:|:-----:|:----:|:---------------:| | |
| | 0.4105 | 1.36 | 1000 | 0.3789 | | |
| | 0.409 | 2.71 | 2000 | 0.3753 | | |
| | 0.4076 | 4.07 | 3000 | 0.3735 | | |
| | 0.4055 | 5.43 | 4000 | 0.3719 | | |
| ### Framework versions | |
| - Transformers 4.30.0.dev0 | |
| - Pytorch 2.0.1+cu118 | |
| - Datasets 2.13.0 | |
| - Tokenizers 0.13.3 | |