update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,7 +2,6 @@
|
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
- text-to-speech
|
| 6 |
datasets:
|
| 7 |
- facebook/voxpopuli
|
| 8 |
model-index:
|
|
@@ -16,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# speecht5_finetuned_voxpopuli_nl
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli dataset.
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -45,9 +46,19 @@ The following hyperparameters were used during training:
|
|
| 45 |
- lr_scheduler_warmup_steps: 500
|
| 46 |
- training_steps: 4000
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- Transformers 4.30.2
|
| 51 |
- Pytorch 2.0.1+cu118
|
| 52 |
- Datasets 2.13.1
|
| 53 |
-
- Tokenizers 0.13.3
|
|
|
|
| 2 |
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
| 5 |
datasets:
|
| 6 |
- facebook/voxpopuli
|
| 7 |
model-index:
|
|
|
|
| 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 facebook/voxpopuli dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4572
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 46 |
- lr_scheduler_warmup_steps: 500
|
| 47 |
- training_steps: 4000
|
| 48 |
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 0.5221 | 4.3 | 1000 | 0.4774 |
|
| 54 |
+
| 0.505 | 8.61 | 2000 | 0.4648 |
|
| 55 |
+
| 0.4929 | 12.91 | 3000 | 0.4583 |
|
| 56 |
+
| 0.4901 | 17.21 | 4000 | 0.4572 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
- Transformers 4.30.2
|
| 62 |
- Pytorch 2.0.1+cu118
|
| 63 |
- Datasets 2.13.1
|
| 64 |
+
- Tokenizers 0.13.3
|