speecht5_finetuned_iamwille_ig
This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4255
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.8142 | 0.1364 | 100 | 0.5158 |
| 4.4829 | 0.2729 | 200 | 0.5417 |
| 4.2847 | 0.4093 | 300 | 0.4858 |
| 4.1648 | 0.5457 | 400 | 0.4760 |
| 4.1417 | 0.6821 | 500 | 0.4716 |
| 4.2032 | 0.8186 | 600 | 0.4722 |
| 4.1184 | 0.9550 | 700 | 0.4868 |
| 4.0658 | 1.0914 | 800 | 0.4759 |
| 4.0502 | 1.2278 | 900 | 0.4640 |
| 4.0098 | 1.3643 | 1000 | 0.4575 |
| 3.9671 | 1.5007 | 1100 | 0.4547 |
| 3.9913 | 1.6371 | 1200 | 0.4676 |
| 3.9387 | 1.7735 | 1300 | 0.4522 |
| 3.8744 | 1.9100 | 1400 | 0.4534 |
| 3.9864 | 2.0464 | 1500 | 0.4611 |
| 3.9376 | 2.1828 | 1600 | 0.4563 |
| 3.8866 | 2.3192 | 1700 | 0.4475 |
| 3.9037 | 2.4557 | 1800 | 0.4476 |
| 3.8385 | 2.5921 | 1900 | 0.4477 |
| 3.8257 | 2.7285 | 2000 | 0.4489 |
| 3.7905 | 2.8649 | 2100 | 0.4466 |
| 3.8109 | 3.0014 | 2200 | 0.4447 |
| 3.7939 | 3.1378 | 2300 | 0.4450 |
| 3.8064 | 3.2742 | 2400 | 0.4432 |
| 3.7764 | 3.4106 | 2500 | 0.4404 |
| 3.7865 | 3.5471 | 2600 | 0.4419 |
| 3.7751 | 3.6835 | 2700 | 0.4385 |
| 3.7756 | 3.8199 | 2800 | 0.4401 |
| 3.7690 | 3.9563 | 2900 | 0.4395 |
| 3.7346 | 4.0928 | 3000 | 0.4365 |
| 3.7100 | 4.2292 | 3100 | 0.4382 |
| 3.7393 | 4.3656 | 3200 | 0.4390 |
| 3.7059 | 4.5020 | 3300 | 0.4330 |
| 3.7070 | 4.6385 | 3400 | 0.4366 |
| 3.7473 | 4.7749 | 3500 | 0.4343 |
| 3.6961 | 4.9113 | 3600 | 0.4317 |
| 3.6602 | 5.0477 | 3700 | 0.4318 |
| 3.6724 | 5.1842 | 3800 | 0.4306 |
| 3.6902 | 5.3206 | 3900 | 0.4318 |
| 3.7066 | 5.4570 | 4000 | 0.4321 |
| 3.6924 | 5.5935 | 4100 | 0.4284 |
| 3.6851 | 5.7299 | 4200 | 0.4265 |
| 3.6385 | 5.8663 | 4300 | 0.4272 |
| 3.6388 | 6.0027 | 4400 | 0.4271 |
| 3.6214 | 6.1392 | 4500 | 0.4272 |
| 3.6388 | 6.2756 | 4600 | 0.4263 |
| 3.6027 | 6.4120 | 4700 | 0.4286 |
| 3.6368 | 6.5484 | 4800 | 0.4266 |
| 3.5963 | 6.6849 | 4900 | 0.4264 |
| 3.6028 | 6.8213 | 5000 | 0.4255 |
Framework versions
- Transformers 5.15.1
- Pytorch 2.13.0
- Datasets 5.0.1
- Tokenizers 0.22.2