update model card README.md
Browse files
README.md
CHANGED
|
@@ -18,12 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the single_speaker_en_test_librivox dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
-
|
| 22 |
-
- eval_runtime: 98.0533
|
| 23 |
-
- eval_samples_per_second: 50.962
|
| 24 |
-
- eval_steps_per_second: 25.486
|
| 25 |
-
- epoch: 1.78
|
| 26 |
-
- step: 5000
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -53,6 +48,17 @@ The following hyperparameters were used during training:
|
|
| 53 |
- lr_scheduler_warmup_steps: 500
|
| 54 |
- num_epochs: 3.0
|
| 55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
### Framework versions
|
| 57 |
|
| 58 |
- Transformers 4.31.0.dev0
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the single_speaker_en_test_librivox dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.5817
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 48 |
- lr_scheduler_warmup_steps: 500
|
| 49 |
- num_epochs: 3.0
|
| 50 |
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
+
| 0.8228 | 0.59 | 1000 | 0.7680 |
|
| 56 |
+
| 0.74 | 1.19 | 2000 | 0.6693 |
|
| 57 |
+
| 0.6854 | 1.78 | 3000 | 0.6155 |
|
| 58 |
+
| 0.6794 | 2.37 | 4000 | 0.5908 |
|
| 59 |
+
| 0.658 | 2.97 | 5000 | 0.5817 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
- Transformers 4.31.0.dev0
|