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 |
|---|---|---|---|
| 0.07 | 62.5079 | 1000 | 0.0638 |
| 0.0564 | 125.0 | 2000 | 0.0597 |
| 0.0488 | 187.5079 | 3000 | 0.0594 |
| 0.0441 | 250.0 | 4000 | 0.0628 |
| 0.0399 | 312.5079 | 5000 | 0.0633 |
| 0.0377 | 375.0 | 6000 | 0.0637 |
| 0.0356 | 437.5079 | 7000 | 0.0710 |
| 0.0325 | 500.0 | 8000 | 0.0679 |
| 0.0317 | 562.5079 | 9000 | 0.0668 |
| 0.0303 | 625.0 | 10000 | 0.0708 |
| 0.0292 | 687.5079 | 11000 | 0.0699 |
| 0.0294 | 750.0 | 12000 | 0.0747 |
| 0.0277 | 812.5079 | 13000 | 0.0737 |
| 0.0272 | 875.0 | 14000 | 0.0709 |
| 0.026 | 937.5079 | 15000 | 0.0728 |
| 0.0264 | 1000.0 | 16000 | 0.0738 |
| 0.027 | 1062.5079 | 17000 | 0.0738 |
| 0.0261 | 1125.0 | 18000 | 0.0742 |
| 0.026 | 1187.5079 | 19000 | 0.0749 |
| 0.0289 | 1250.0 | 20000 | 0.0740 |
model.safetensors 578 MBtraining_args.bin 6.1 kBmicrosoft/speecht5_tts