update model card README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# speecht5_finetuned_voxpopuli_lt
|
| 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 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -44,6 +46,16 @@ The following hyperparameters were used during training:
|
|
| 44 |
- lr_scheduler_warmup_steps: 500
|
| 45 |
- training_steps: 4000
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
- Transformers 4.30.2
|
|
|
|
| 15 |
# speecht5_finetuned_voxpopuli_lt
|
| 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: 0.5034
|
| 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 |
+
| 0.4877 | 103.9 | 1000 | 0.4923 |
|
| 54 |
+
| 0.458 | 207.79 | 2000 | 0.5039 |
|
| 55 |
+
| 0.4439 | 311.69 | 3000 | 0.4976 |
|
| 56 |
+
| 0.4407 | 415.58 | 4000 | 0.5034 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
- Transformers 4.30.2
|