speecht5_allvoices
This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4390
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: 10000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.5406 | 0.69 | 1000 | 0.5013 |
0.5066 | 1.39 | 2000 | 0.4761 |
0.4932 | 2.08 | 3000 | 0.4670 |
0.483 | 2.77 | 4000 | 0.4551 |
0.4698 | 3.47 | 5000 | 0.4507 |
0.4726 | 4.16 | 6000 | 0.4461 |
0.4685 | 4.85 | 7000 | 0.4426 |
0.4746 | 5.54 | 8000 | 0.4413 |
0.4689 | 6.24 | 9000 | 0.4418 |
0.4638 | 6.93 | 10000 | 0.4390 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0