This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6222 | 1.0 | 23 | 0.5343 |
| 0.5615 | 2.0 | 46 | 0.4726 |
| 0.4977 | 3.0 | 69 | 0.4351 |
| 0.466 | 4.0 | 92 | 0.4238 |
| 0.4454 | 5.0 | 115 | 0.4318 |
| 0.4275 | 6.0 | 138 | 0.3951 |
| 0.4206 | 7.0 | 161 | 0.3955 |
| 0.4019 | 8.0 | 184 | 0.3981 |
| 0.4069 | 9.0 | 207 | 0.3878 |
| 0.3949 | 10.0 | 230 | 0.3778 |
| 0.3868 | 11.0 | 253 | 0.3760 |
| 0.3818 | 12.0 | 276 | 0.3742 |
| 0.3787 | 13.0 | 299 | 0.3767 |
| 0.3763 | 14.0 | 322 | 0.3749 |
| 0.3806 | 15.0 | 345 | 0.3734 |
| 0.3707 | 16.0 | 368 | 0.3699 |
| 0.3673 | 17.0 | 391 | 0.3766 |
| 0.3637 | 18.0 | 414 | 0.3702 |
| 0.3652 | 19.0 | 437 | 0.3736 |
| 0.3594 | 20.0 | 460 | 0.3750 |
model.safetensors 578 MBtraining_args.bin 5.5 kB