Ejaz Habib Dar
commited on
Commit
•
b612298
1
Parent(s):
2afaa44
update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,8 +2,6 @@
|
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
datasets:
|
| 6 |
-
- common_voice_13_0
|
| 7 |
model-index:
|
| 8 |
- name: speecht5_finetuned_voxpopuli_nl
|
| 9 |
results: []
|
|
@@ -14,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# speecht5_finetuned_voxpopuli_nl
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -50,10 +48,10 @@ 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
|
|
|
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: speecht5_finetuned_voxpopuli_nl
|
| 7 |
results: []
|
|
|
|
| 12 |
|
| 13 |
# speecht5_finetuned_voxpopuli_nl
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.4881
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 0.5694 | 3.73 | 1000 | 0.5130 |
|
| 52 |
+
| 0.5397 | 7.45 | 2000 | 0.4972 |
|
| 53 |
+
| 0.5231 | 11.18 | 3000 | 0.4907 |
|
| 54 |
+
| 0.5196 | 14.9 | 4000 | 0.4881 |
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|