End of training
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 voxpopuli dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
-
|
| 22 |
-
- eval_runtime: 10.4047
|
| 23 |
-
- eval_samples_per_second: 22.298
|
| 24 |
-
- eval_steps_per_second: 11.149
|
| 25 |
-
- epoch: 30.3071
|
| 26 |
-
- step: 2000
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -54,6 +49,16 @@ The following hyperparameters were used during training:
|
|
| 54 |
- training_steps: 4000
|
| 55 |
- mixed_precision_training: Native AMP
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- Transformers 4.48.2
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4309
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 49 |
- training_steps: 4000
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 56 |
+
| 0.4649 | 15.1536 | 1000 | 0.4475 |
|
| 57 |
+
| 0.4501 | 30.3071 | 2000 | 0.4368 |
|
| 58 |
+
| 0.4556 | 45.9367 | 3000 | 0.4321 |
|
| 59 |
+
| 0.434 | 61.0768 | 4000 | 0.4309 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
- Transformers 4.48.2
|