Commit
•
adc385b
1
Parent(s):
6bab9e1
update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/speecht5_hifigan](https://huggingface.co/microsoft/speecht5_hifigan) on the facebook/voxpopuli_nl dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/speecht5_hifigan](https://huggingface.co/microsoft/speecht5_hifigan) on the facebook/voxpopuli_nl dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4598
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 0.5237 | 4.3 | 1000 | 0.4788 |
|
| 54 |
+
| 0.4974 | 8.61 | 2000 | 0.4652 |
|
| 55 |
+
| 0.4941 | 12.91 | 3000 | 0.4634 |
|
| 56 |
+
| 0.4925 | 17.21 | 4000 | 0.4598 |
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|