This model is a fine-tuned version of ckandemir/speecht5_finetuned_voxpopuli_fr on the GuianeseCreole 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 |
|---|---|---|---|
| 0.6066 | 3.4622 | 100 | 0.5097 |
| 0.5214 | 6.9244 | 200 | 0.4894 |
| 0.4879 | 10.3556 | 300 | 0.4819 |
| 0.4856 | 13.8178 | 400 | 0.4706 |
| 0.4704 | 17.2489 | 500 | 0.4692 |
| 0.4676 | 20.7111 | 600 | 0.4684 |
| 0.4592 | 24.1422 | 700 | 0.4669 |
| 0.4593 | 27.6044 | 800 | 0.4664 |
| 0.4556 | 31.0356 | 900 | 0.4662 |
model.safetensors 578 MBtraining_args.bin 5.9 kB