End of training
Browse files
README.md
CHANGED
|
@@ -19,12 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Common Voice 11.0 dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
-
|
| 23 |
-
- eval_runtime: 32.2362
|
| 24 |
-
- eval_samples_per_second: 45.446
|
| 25 |
-
- eval_steps_per_second: 5.708
|
| 26 |
-
- epoch: 2.4272
|
| 27 |
-
- step: 1000
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
@@ -55,6 +50,16 @@ The following hyperparameters were used during training:
|
|
| 55 |
- training_steps: 4000
|
| 56 |
- mixed_precision_training: Native AMP
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
### Framework versions
|
| 59 |
|
| 60 |
- Transformers 4.41.0.dev0
|
|
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the Common Voice 11.0 dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.4979
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 50 |
- training_steps: 4000
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
+
| 0.5633 | 2.4272 | 1000 | 0.5130 |
|
| 58 |
+
| 0.5464 | 4.8544 | 2000 | 0.5075 |
|
| 59 |
+
| 0.5336 | 7.2816 | 3000 | 0.4988 |
|
| 60 |
+
| 0.5334 | 9.7087 | 4000 | 0.4979 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
### Framework versions
|
| 64 |
|
| 65 |
- Transformers 4.41.0.dev0
|