gyi-LUK-audio-aligned-speecht5
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: 0.0899
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 2000
- training_steps: 20000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.093 | 50.0 | 1000 | 0.0865 |
| 0.0751 | 100.0 | 2000 | 0.0819 |
| 0.0725 | 150.0 | 3000 | 0.0800 |
| 0.0564 | 200.0 | 4000 | 0.0813 |
| 0.0531 | 250.0 | 5000 | 0.0804 |
| 0.0484 | 300.0 | 6000 | 0.0812 |
| 0.0466 | 350.0 | 7000 | 0.0824 |
| 0.0427 | 400.0 | 8000 | 0.0868 |
| 0.0417 | 450.0 | 9000 | 0.0871 |
| 0.0646 | 500.0 | 10000 | 0.0864 |
| 0.0387 | 550.0 | 11000 | 0.0881 |
| 0.0409 | 600.0 | 12000 | 0.0878 |
| 0.0389 | 650.0 | 13000 | 0.0890 |
| 0.0422 | 700.0 | 14000 | 0.0891 |
| 0.0428 | 750.0 | 15000 | 0.0894 |
| 0.0424 | 800.0 | 16000 | 0.0891 |
| 0.0441 | 850.0 | 17000 | 0.0897 |
| 0.044 | 900.0 | 18000 | 0.0906 |
| 0.0365 | 950.0 | 19000 | 0.0906 |
| 0.0359 | 1000.0 | 20000 | 0.0899 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu128
- Datasets 4.2.0
- Tokenizers 0.22.2