This model is a fine-tuned version of microsoft/speecht5_tts on the voxpopuli 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 |
|---|---|---|---|
| 0.5914 | 4.5872 | 500 | 0.5307 |
| 0.5483 | 9.1743 | 1000 | 0.5039 |
| 0.5397 | 13.7615 | 1500 | 0.4955 |
| 0.5199 | 18.3486 | 2000 | 0.4885 |
| 0.5161 | 22.9358 | 2500 | 0.4878 |
| 0.5125 | 27.5229 | 3000 | 0.4847 |
| 0.5169 | 32.1101 | 3500 | 0.4847 |
| 0.5105 | 36.6972 | 4000 | 0.4837 |
| 0.5058 | 41.2844 | 4500 | 0.4823 |
| 0.5058 | 45.8716 | 5000 | 0.4829 |
model.safetensors 578 MBtraining_args.bin 6 kBmicrosoft/speecht5_tts