Commit
•
e6b209f
1
Parent(s):
2ac8e6f
End of training
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -53,15 +53,15 @@ The following hyperparameters were used during training:
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
- Transformers 4.34.0.dev0
|
| 65 |
- Pytorch 2.0.1+cu118
|
| 66 |
-
- Datasets 2.14.
|
| 67 |
- Tokenizers 0.13.3
|
|
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.4441
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
+
| 0.5058 | 4.32 | 1000 | 0.4640 |
|
| 57 |
+
| 0.4873 | 8.64 | 2000 | 0.4512 |
|
| 58 |
+
| 0.4917 | 12.96 | 3000 | 0.4465 |
|
| 59 |
+
| 0.4845 | 17.28 | 4000 | 0.4441 |
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
- Transformers 4.34.0.dev0
|
| 65 |
- Pytorch 2.0.1+cu118
|
| 66 |
+
- Datasets 2.14.4
|
| 67 |
- Tokenizers 0.13.3
|