End of training
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -52,10 +52,10 @@ The following hyperparameters were used during training:
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.4594
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
+
| 0.5206 | 4.3 | 1000 | 0.4793 |
|
| 56 |
+
| 0.4947 | 8.61 | 2000 | 0.4663 |
|
| 57 |
+
| 0.4931 | 12.91 | 3000 | 0.4632 |
|
| 58 |
+
| 0.4903 | 17.21 | 4000 | 0.4594 |
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|