SpeechT5 TTS LJ_Speech
This model is a fine-tuned version of microsoft/speecht5_tts on the lj_speech dataset. It achieves the following results on the evaluation set:
- Loss: 0.3659
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: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4059 | 2.7137 | 1000 | 0.3729 |
| 0.3927 | 5.4274 | 2000 | 0.3707 |
| 0.3982 | 8.1411 | 3000 | 0.3696 |
| 0.4006 | 10.8548 | 4000 | 0.3682 |
| 0.3869 | 13.5685 | 5000 | 0.3669 |
| 0.395 | 16.2822 | 6000 | 0.3669 |
| 0.4012 | 18.9959 | 7000 | 0.3666 |
| 0.3858 | 21.7096 | 8000 | 0.3662 |
| 0.3864 | 24.4233 | 9000 | 0.3658 |
| 0.3982 | 27.1370 | 10000 | 0.3659 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 49